id
stringlengths
2
214
conversations
listlengths
2
42
data_source
stringclasses
54 values
cauldron/dvqa/images/dvqa_00099499.png
[ { "from": "human", "value": "Which algorithm has the highest accuracy?\nAnswer the question using a single word or phrase." }, { "from": "gpt", "value": "Slope." }, { "from": "human", "value": "Which algorithm has the lowest accuracy?" }, { "from": "gpt", "value": "Pistol." }, { "from": "human", "value": "What is the accuracy of the algorithm with highest accuracy?" }, { "from": "gpt", "value": "5." }, { "from": "human", "value": "What is the accuracy of the algorithm with lowest accuracy?" }, { "from": "gpt", "value": "2." }, { "from": "human", "value": "How much more accurate is the most accurate algorithm compared the least accurate algorithm?" }, { "from": "gpt", "value": "3." }, { "from": "human", "value": "How many algorithms have accuracies higher than 4?" }, { "from": "gpt", "value": "One." }, { "from": "human", "value": "What is the sum of the accuracies of the algorithms slope and wise?" }, { "from": "gpt", "value": "9." }, { "from": "human", "value": "Is the accuracy of the algorithm pistol larger than slope?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "Are the values in the chart presented in a percentage scale?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "What is the accuracy of the algorithm pistol?" }, { "from": "gpt", "value": "2." }, { "from": "human", "value": "What is the label of the first bar from the left?" }, { "from": "gpt", "value": "Slope." } ]
dvqa(cauldron,llava_format)
cauldron/dvqa/images/dvqa_00099501.png
[ { "from": "human", "value": "How many algorithms have accuracy lower than 6 in at least one dataset?\nAnswer the question using a single word or phrase." }, { "from": "gpt", "value": "Six." }, { "from": "human", "value": "Which algorithm has lowest accuracy for any dataset?" }, { "from": "gpt", "value": "Side." }, { "from": "human", "value": "What is the lowest accuracy reported in the whole chart?" }, { "from": "gpt", "value": "1." }, { "from": "human", "value": "What is the sum of accuracies of the algorithm scheme for all the datasets?" }, { "from": "gpt", "value": "19." }, { "from": "human", "value": "Is the accuracy of the algorithm scheme in the dataset verse smaller than the accuracy of the algorithm store in the dataset pain?" }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "What dataset does the red color represent?" }, { "from": "gpt", "value": "Prayer." }, { "from": "human", "value": "What is the accuracy of the algorithm scheme in the dataset pain?" }, { "from": "gpt", "value": "7." }, { "from": "human", "value": "What is the label of the sixth group of bars from the bottom?" }, { "from": "gpt", "value": "Scheme." }, { "from": "human", "value": "What is the label of the second bar from the bottom in each group?" }, { "from": "gpt", "value": "Pain." }, { "from": "human", "value": "Are the bars horizontal?" }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "Is each bar a single solid color without patterns?" }, { "from": "gpt", "value": "Yes." } ]
dvqa(cauldron,llava_format)
cauldron/dvqa/images/dvqa_00099504.png
[ { "from": "human", "value": "How many groups of bars contain at least one bar with value greater than 1?\nAnswer the question using a single word or phrase." }, { "from": "gpt", "value": "Four." }, { "from": "human", "value": "Which group of bars contains the smallest valued individual bar in the whole chart?" }, { "from": "gpt", "value": "Strike." }, { "from": "human", "value": "What is the value of the smallest individual bar in the whole chart?" }, { "from": "gpt", "value": "1." }, { "from": "human", "value": "Which group has the smallest summed value?" }, { "from": "gpt", "value": "Vertex." }, { "from": "human", "value": "Which group has the largest summed value?" }, { "from": "gpt", "value": "Grace." }, { "from": "human", "value": "What is the sum of all the values in the strike group?" }, { "from": "gpt", "value": "25." }, { "from": "human", "value": "Is the value of strike in extent larger than the value of affair in leader?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "What element does the forestgreen color represent?" }, { "from": "gpt", "value": "Sex." }, { "from": "human", "value": "What is the value of sex in strike?" }, { "from": "gpt", "value": "7." }, { "from": "human", "value": "What is the label of the third group of bars from the bottom?" }, { "from": "gpt", "value": "Affair." }, { "from": "human", "value": "What is the label of the second bar from the bottom in each group?" }, { "from": "gpt", "value": "Extent." }, { "from": "human", "value": "Are the bars horizontal?" }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "How many bars are there per group?" }, { "from": "gpt", "value": "Four." } ]
dvqa(cauldron,llava_format)
cauldron/dvqa/images/dvqa_00099513.png
[ { "from": "human", "value": "How many objects are preferred by less than 7 people in at least one category?\nAnswer the question using a single word or phrase." }, { "from": "gpt", "value": "Six." }, { "from": "human", "value": "Which object is the most preferred in any category?" }, { "from": "gpt", "value": "Fluid." }, { "from": "human", "value": "How many people like the most preferred object in the whole chart?" }, { "from": "gpt", "value": "9." }, { "from": "human", "value": "Which object is preferred by the least number of people summed across all the categories?" }, { "from": "gpt", "value": "Leg." }, { "from": "human", "value": "Which object is preferred by the most number of people summed across all the categories?" }, { "from": "gpt", "value": "Fluid." }, { "from": "human", "value": "How many total people preferred the object snow across all the categories?" }, { "from": "gpt", "value": "8." }, { "from": "human", "value": "Is the object brass in the category chief preferred by more people than the object fluid in the category cow?" }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "How many people prefer the object hero in the category chief?" }, { "from": "gpt", "value": "5." }, { "from": "human", "value": "What is the label of the first stack of bars from the left?" }, { "from": "gpt", "value": "Nation." }, { "from": "human", "value": "What is the label of the second element from the bottom in each stack of bars?" }, { "from": "gpt", "value": "Cow." }, { "from": "human", "value": "Are the bars horizontal?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "Does the chart contain stacked bars?" }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "How many elements are there in each stack of bars?" }, { "from": "gpt", "value": "Two." } ]
dvqa(cauldron,llava_format)
cauldron/dvqa/images/dvqa_00099515.png
[ { "from": "human", "value": "How many groups of bars contain at least one bar with value greater than 6?\nAnswer the question using a single word or phrase." }, { "from": "gpt", "value": "Two." }, { "from": "human", "value": "Which group of bars contains the largest valued individual bar in the whole chart?" }, { "from": "gpt", "value": "Spite." }, { "from": "human", "value": "What is the value of the largest individual bar in the whole chart?" }, { "from": "gpt", "value": "9." }, { "from": "human", "value": "Which group has the smallest summed value?" }, { "from": "gpt", "value": "Market." }, { "from": "human", "value": "Which group has the largest summed value?" }, { "from": "gpt", "value": "Spite." }, { "from": "human", "value": "What is the sum of all the values in the tone group?" }, { "from": "gpt", "value": "23." }, { "from": "human", "value": "Is the value of book in hair larger than the value of tone in radar?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "What element does the goldenrod color represent?" }, { "from": "gpt", "value": "Radar." }, { "from": "human", "value": "What is the value of radar in market?" }, { "from": "gpt", "value": "1." }, { "from": "human", "value": "What is the label of the third group of bars from the bottom?" }, { "from": "gpt", "value": "Market." }, { "from": "human", "value": "What is the label of the second bar from the bottom in each group?" }, { "from": "gpt", "value": "Firm." }, { "from": "human", "value": "Are the bars horizontal?" }, { "from": "gpt", "value": "Yes." } ]
dvqa(cauldron,llava_format)
cauldron/dvqa/images/dvqa_00099516.png
[ { "from": "human", "value": "Which item sold the most units?\nAnswer the question using a single word or phrase." }, { "from": "gpt", "value": "Tale." }, { "from": "human", "value": "Which item sold the least units?" }, { "from": "gpt", "value": "Graph." }, { "from": "human", "value": "How many units of the the most sold item were sold?" }, { "from": "gpt", "value": "8." }, { "from": "human", "value": "How many units of the the least sold item were sold?" }, { "from": "gpt", "value": "1." }, { "from": "human", "value": "How many more of the most sold item were sold compared to the least sold item?" }, { "from": "gpt", "value": "7." }, { "from": "human", "value": "How many items sold more than 1 units?" }, { "from": "gpt", "value": "Three." }, { "from": "human", "value": "How many units of items bed and rail were sold?" }, { "from": "gpt", "value": "12." }, { "from": "human", "value": "Did the item bed sold more units than graph?" }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "How many units of the item bed were sold?" }, { "from": "gpt", "value": "6." }, { "from": "human", "value": "What is the label of the first bar from the bottom?" }, { "from": "gpt", "value": "Rail." }, { "from": "human", "value": "Are the bars horizontal?" }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "How many bars are there?" }, { "from": "gpt", "value": "Four." } ]
dvqa(cauldron,llava_format)
cauldron/dvqa/images/dvqa_00099522.png
[ { "from": "human", "value": "Which algorithm has the highest accuracy?\nAnswer the question using a single word or phrase." }, { "from": "gpt", "value": "Defeat." }, { "from": "human", "value": "Which algorithm has the lowest accuracy?" }, { "from": "gpt", "value": "Excess." }, { "from": "human", "value": "What is the accuracy of the algorithm with highest accuracy?" }, { "from": "gpt", "value": "9." }, { "from": "human", "value": "What is the accuracy of the algorithm with lowest accuracy?" }, { "from": "gpt", "value": "1." }, { "from": "human", "value": "How much more accurate is the most accurate algorithm compared the least accurate algorithm?" }, { "from": "gpt", "value": "8." }, { "from": "human", "value": "How many algorithms have accuracies higher than 1?" }, { "from": "gpt", "value": "Three." }, { "from": "human", "value": "What is the sum of the accuracies of the algorithms defeat and excess?" }, { "from": "gpt", "value": "10." }, { "from": "human", "value": "Is the accuracy of the algorithm game larger than defeat?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "What is the accuracy of the algorithm excess?" }, { "from": "gpt", "value": "1." }, { "from": "human", "value": "What is the label of the second bar from the bottom?" }, { "from": "gpt", "value": "Defeat." }, { "from": "human", "value": "Are the bars horizontal?" }, { "from": "gpt", "value": "Yes." } ]
dvqa(cauldron,llava_format)
cauldron/dvqa/images/dvqa_00099532.png
[ { "from": "human", "value": "Which object is the most preferred?\nAnswer the question using a single word or phrase." }, { "from": "gpt", "value": "Gun." }, { "from": "human", "value": "Which object is the least preferred?" }, { "from": "gpt", "value": "Mail." }, { "from": "human", "value": "How many people prefer the most preferred object?" }, { "from": "gpt", "value": "9." }, { "from": "human", "value": "How many people prefer the least preferred object?" }, { "from": "gpt", "value": "2." }, { "from": "human", "value": "What is the difference between most and least preferred object?" }, { "from": "gpt", "value": "7." }, { "from": "human", "value": "How many objects are liked by more than 7 people?" }, { "from": "gpt", "value": "Three." }, { "from": "human", "value": "How many people prefer the objects midst or mad?" }, { "from": "gpt", "value": "13." }, { "from": "human", "value": "Is the object plenty preferred by less people than knife?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "How many people prefer the object midst?" }, { "from": "gpt", "value": "5." }, { "from": "human", "value": "What is the label of the first bar from the left?" }, { "from": "gpt", "value": "Gun." }, { "from": "human", "value": "Are the bars horizontal?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "Does the chart contain stacked bars?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "Is each bar a single solid color without patterns?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "How many bars are there?" }, { "from": "gpt", "value": "Eight." } ]
dvqa(cauldron,llava_format)
cauldron/dvqa/images/dvqa_00099533.png
[ { "from": "human", "value": "How many groups of bars contain at least one bar with value greater than -3?\nAnswer the question using a single word or phrase." }, { "from": "gpt", "value": "Two." }, { "from": "human", "value": "Which group of bars contains the largest valued individual bar in the whole chart?" }, { "from": "gpt", "value": "Slave." }, { "from": "human", "value": "Which group of bars contains the smallest valued individual bar in the whole chart?" }, { "from": "gpt", "value": "Slave." }, { "from": "human", "value": "What is the value of the largest individual bar in the whole chart?" }, { "from": "gpt", "value": "7." }, { "from": "human", "value": "What is the value of the smallest individual bar in the whole chart?" }, { "from": "gpt", "value": "-3." }, { "from": "human", "value": "Which group has the smallest summed value?" }, { "from": "gpt", "value": "Slave." }, { "from": "human", "value": "Which group has the largest summed value?" }, { "from": "gpt", "value": "Beard." }, { "from": "human", "value": "Is the value of slave in mood smaller than the value of beard in city?" }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "Are the values in the chart presented in a percentage scale?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "What element does the steelblue color represent?" }, { "from": "gpt", "value": "City." }, { "from": "human", "value": "What is the value of mood in beard?" }, { "from": "gpt", "value": "3." }, { "from": "human", "value": "What is the label of the first group of bars from the bottom?" }, { "from": "gpt", "value": "Beard." }, { "from": "human", "value": "What is the label of the first bar from the bottom in each group?" }, { "from": "gpt", "value": "City." }, { "from": "human", "value": "Does the chart contain any negative values?" }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "Are the bars horizontal?" }, { "from": "gpt", "value": "Yes." } ]
dvqa(cauldron,llava_format)
cauldron/dvqa/images/dvqa_00099536.png
[ { "from": "human", "value": "Which algorithm has the highest accuracy?\nAnswer the question using a single word or phrase." }, { "from": "gpt", "value": "Midst." }, { "from": "human", "value": "What is the accuracy of the algorithm with highest accuracy?" }, { "from": "gpt", "value": "9." }, { "from": "human", "value": "How many algorithms have accuracies higher than 1?" }, { "from": "gpt", "value": "Four." }, { "from": "human", "value": "What is the sum of the accuracies of the algorithms woman and pilot?" }, { "from": "gpt", "value": "6." }, { "from": "human", "value": "Is the accuracy of the algorithm fluid larger than woman?" }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "What is the accuracy of the algorithm pilot?" }, { "from": "gpt", "value": "5." }, { "from": "human", "value": "What is the label of the first bar from the left?" }, { "from": "gpt", "value": "Fluid." }, { "from": "human", "value": "Are the bars horizontal?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "Does the chart contain stacked bars?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "Is each bar a single solid color without patterns?" }, { "from": "gpt", "value": "Yes." } ]
dvqa(cauldron,llava_format)
cauldron/dvqa/images/dvqa_00099539.png
[ { "from": "human", "value": "How many items sold less than 5 units in at least one store?\nAnswer the question using a single word or phrase." }, { "from": "gpt", "value": "Five." }, { "from": "human", "value": "Which item sold the most units in any shop?" }, { "from": "gpt", "value": "Light." }, { "from": "human", "value": "Which item sold the least units in any shop?" }, { "from": "gpt", "value": "Light." }, { "from": "human", "value": "How many units did the best selling item sell in the whole chart?" }, { "from": "gpt", "value": "7." }, { "from": "human", "value": "How many units did the worst selling item sell in the whole chart?" }, { "from": "gpt", "value": "1." }, { "from": "human", "value": "Which item sold the least number of units summed across all the stores?" }, { "from": "gpt", "value": "Ship." }, { "from": "human", "value": "How many units of the item light were sold across all the stores?" }, { "from": "gpt", "value": "8." }, { "from": "human", "value": "Did the item forth in the store effort sold larger units than the item ship in the store mad?" }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "What store does the grey color represent?" }, { "from": "gpt", "value": "Effort." }, { "from": "human", "value": "How many units of the item ship were sold in the store effort?" }, { "from": "gpt", "value": "4." }, { "from": "human", "value": "What is the label of the fifth stack of bars from the left?" }, { "from": "gpt", "value": "Fall." }, { "from": "human", "value": "What is the label of the first element from the bottom in each stack of bars?" }, { "from": "gpt", "value": "Effort." }, { "from": "human", "value": "Does the chart contain stacked bars?" }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "Is each bar a single solid color without patterns?" }, { "from": "gpt", "value": "No." } ]
dvqa(cauldron,llava_format)
cauldron/dvqa/images/dvqa_00099543.png
[ { "from": "human", "value": "Which bar has the largest value?\nAnswer the question using a single word or phrase." }, { "from": "gpt", "value": "Desk." }, { "from": "human", "value": "Which bar has the smallest value?" }, { "from": "gpt", "value": "Action." }, { "from": "human", "value": "What is the value of the largest bar?" }, { "from": "gpt", "value": "80." }, { "from": "human", "value": "What is the value of the smallest bar?" }, { "from": "gpt", "value": "10." }, { "from": "human", "value": "What is the difference between the largest and the smallest value in the chart?" }, { "from": "gpt", "value": "70." }, { "from": "human", "value": "How many bars have values larger than 20?" }, { "from": "gpt", "value": "Six." }, { "from": "human", "value": "Is the value of leg larger than burden?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "Are the values in the chart presented in a percentage scale?" }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "What is the value of threat?" }, { "from": "gpt", "value": "60." }, { "from": "human", "value": "What is the label of the eighth bar from the bottom?" }, { "from": "gpt", "value": "Burden." }, { "from": "human", "value": "Are the bars horizontal?" }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "How many bars are there?" }, { "from": "gpt", "value": "Eight." } ]
dvqa(cauldron,llava_format)
cauldron/dvqa/images/dvqa_00099545.png
[ { "from": "human", "value": "Which algorithm has the highest accuracy?\nAnswer the question using a single word or phrase." }, { "from": "gpt", "value": "Boat." }, { "from": "human", "value": "Which algorithm has the lowest accuracy?" }, { "from": "gpt", "value": "Unit." }, { "from": "human", "value": "What is the accuracy of the algorithm with highest accuracy?" }, { "from": "gpt", "value": "6." }, { "from": "human", "value": "What is the accuracy of the algorithm with lowest accuracy?" }, { "from": "gpt", "value": "1." }, { "from": "human", "value": "How much more accurate is the most accurate algorithm compared the least accurate algorithm?" }, { "from": "gpt", "value": "5." }, { "from": "human", "value": "How many algorithms have accuracies lower than 6?" }, { "from": "gpt", "value": "Four." }, { "from": "human", "value": "What is the sum of the accuracies of the algorithms boat and object?" }, { "from": "gpt", "value": "10." }, { "from": "human", "value": "Is the accuracy of the algorithm smoke smaller than unit?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "Are the values in the chart presented in a logarithmic scale?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "What is the accuracy of the algorithm smoke?" }, { "from": "gpt", "value": "4." }, { "from": "human", "value": "What is the label of the fifth bar from the bottom?" }, { "from": "gpt", "value": "Object." }, { "from": "human", "value": "Are the bars horizontal?" }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "How many bars are there?" }, { "from": "gpt", "value": "Five." } ]
dvqa(cauldron,llava_format)
cauldron/dvqa/images/dvqa_00099553.png
[ { "from": "human", "value": "Which bar has the largest value?\nAnswer the question using a single word or phrase." }, { "from": "gpt", "value": "Combat." }, { "from": "human", "value": "What is the value of the largest bar?" }, { "from": "gpt", "value": "8." }, { "from": "human", "value": "How many bars have values larger than 8?" }, { "from": "gpt", "value": "Zero." }, { "from": "human", "value": "What is the sum of the values of watch and cycle?" }, { "from": "gpt", "value": "8." }, { "from": "human", "value": "Is the value of speech larger than change?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "Are the values in the chart presented in a percentage scale?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "What is the value of change?" }, { "from": "gpt", "value": "6." }, { "from": "human", "value": "What is the label of the fourth bar from the bottom?" }, { "from": "gpt", "value": "Vision." }, { "from": "human", "value": "Are the bars horizontal?" }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "Is each bar a single solid color without patterns?" }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "How many bars are there?" }, { "from": "gpt", "value": "Seven." } ]
dvqa(cauldron,llava_format)
cauldron/dvqa/images/dvqa_00099561.png
[ { "from": "human", "value": "How many groups of bars contain at least one bar with value greater than 1?\nAnswer the question using a single word or phrase." }, { "from": "gpt", "value": "Six." }, { "from": "human", "value": "Which group of bars contains the smallest valued individual bar in the whole chart?" }, { "from": "gpt", "value": "Charm." }, { "from": "human", "value": "What is the value of the smallest individual bar in the whole chart?" }, { "from": "gpt", "value": "-7." }, { "from": "human", "value": "Which group has the smallest summed value?" }, { "from": "gpt", "value": "Row." }, { "from": "human", "value": "What element does the steelblue color represent?" }, { "from": "gpt", "value": "Screen." }, { "from": "human", "value": "What is the value of screen in charm?" }, { "from": "gpt", "value": "9." }, { "from": "human", "value": "What is the label of the fourth group of bars from the bottom?" }, { "from": "gpt", "value": "Beat." }, { "from": "human", "value": "What is the label of the first bar from the bottom in each group?" }, { "from": "gpt", "value": "Life." }, { "from": "human", "value": "Does the chart contain any negative values?" }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "Are the bars horizontal?" }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "How many bars are there per group?" }, { "from": "gpt", "value": "Two." } ]
dvqa(cauldron,llava_format)
cauldron/dvqa/images/dvqa_00099565.png
[ { "from": "human", "value": "Which object is the most preferred?\nAnswer the question using a single word or phrase." }, { "from": "gpt", "value": "Box." }, { "from": "human", "value": "Which object is the least preferred?" }, { "from": "gpt", "value": "Reply." }, { "from": "human", "value": "How many people prefer the most preferred object?" }, { "from": "gpt", "value": "9." }, { "from": "human", "value": "How many people prefer the least preferred object?" }, { "from": "gpt", "value": "1." }, { "from": "human", "value": "What is the difference between most and least preferred object?" }, { "from": "gpt", "value": "8." }, { "from": "human", "value": "How many objects are liked by less than 1 people?" }, { "from": "gpt", "value": "Zero." }, { "from": "human", "value": "How many people prefer the objects depth or box?" }, { "from": "gpt", "value": "15." }, { "from": "human", "value": "Is the object box preferred by less people than depth?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "Are the values in the chart presented in a percentage scale?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "How many people prefer the object escape?" }, { "from": "gpt", "value": "2." }, { "from": "human", "value": "What is the label of the fourth bar from the bottom?" }, { "from": "gpt", "value": "Escape." }, { "from": "human", "value": "Are the bars horizontal?" }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "How many bars are there?" }, { "from": "gpt", "value": "Five." } ]
dvqa(cauldron,llava_format)
cauldron/dvqa/images/dvqa_00099568.png
[ { "from": "human", "value": "How many algorithms have accuracy lower than 4 in at least one dataset?\nAnswer the question using a single word or phrase." }, { "from": "gpt", "value": "Four." }, { "from": "human", "value": "Which algorithm has the smallest accuracy summed across all the datasets?" }, { "from": "gpt", "value": "Form." }, { "from": "human", "value": "Which algorithm has the largest accuracy summed across all the datasets?" }, { "from": "gpt", "value": "Coffee." }, { "from": "human", "value": "What is the sum of accuracies of the algorithm form for all the datasets?" }, { "from": "gpt", "value": "5." }, { "from": "human", "value": "Is the accuracy of the algorithm form in the dataset bag smaller than the accuracy of the algorithm coffee in the dataset member?" }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "What dataset does the darkorange color represent?" }, { "from": "gpt", "value": "Bag." }, { "from": "human", "value": "What is the accuracy of the algorithm room in the dataset member?" }, { "from": "gpt", "value": "8." }, { "from": "human", "value": "What is the label of the third group of bars from the left?" }, { "from": "gpt", "value": "Coffee." }, { "from": "human", "value": "What is the label of the first bar from the left in each group?" }, { "from": "gpt", "value": "Member." } ]
dvqa(cauldron,llava_format)
cauldron/dvqa/images/dvqa_00099577.png
[ { "from": "human", "value": "How many objects are preferred by less than 6 people in at least one category?\nAnswer the question using a single word or phrase." }, { "from": "gpt", "value": "One." }, { "from": "human", "value": "Which object is the most preferred in any category?" }, { "from": "gpt", "value": "Close." }, { "from": "human", "value": "Which object is the least preferred in any category?" }, { "from": "gpt", "value": "Health." }, { "from": "human", "value": "How many people like the most preferred object in the whole chart?" }, { "from": "gpt", "value": "9." }, { "from": "human", "value": "How many people like the least preferred object in the whole chart?" }, { "from": "gpt", "value": "3." }, { "from": "human", "value": "Which object is preferred by the least number of people summed across all the categories?" }, { "from": "gpt", "value": "Health." }, { "from": "human", "value": "Which object is preferred by the most number of people summed across all the categories?" }, { "from": "gpt", "value": "Close." }, { "from": "human", "value": "How many total people preferred the object health across all the categories?" }, { "from": "gpt", "value": "9." }, { "from": "human", "value": "Is the object health in the category pack preferred by more people than the object close in the category scene?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "What category does the steelblue color represent?" }, { "from": "gpt", "value": "Pack." }, { "from": "human", "value": "How many people prefer the object close in the category pack?" }, { "from": "gpt", "value": "9." }, { "from": "human", "value": "What is the label of the second stack of bars from the left?" }, { "from": "gpt", "value": "Health." }, { "from": "human", "value": "What is the label of the first element from the bottom in each stack of bars?" }, { "from": "gpt", "value": "Pack." }, { "from": "human", "value": "Are the bars horizontal?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "Does the chart contain stacked bars?" }, { "from": "gpt", "value": "Yes." } ]
dvqa(cauldron,llava_format)
cauldron/dvqa/images/dvqa_00099579.png
[ { "from": "human", "value": "Which bar has the largest value?\nAnswer the question using a single word or phrase." }, { "from": "gpt", "value": "Target." }, { "from": "human", "value": "Which bar has the smallest value?" }, { "from": "gpt", "value": "Boy." }, { "from": "human", "value": "What is the value of the largest bar?" }, { "from": "gpt", "value": "80." }, { "from": "human", "value": "What is the value of the smallest bar?" }, { "from": "gpt", "value": "40." }, { "from": "human", "value": "What is the difference between the largest and the smallest value in the chart?" }, { "from": "gpt", "value": "40." }, { "from": "human", "value": "How many bars have values larger than 70?" }, { "from": "gpt", "value": "One." }, { "from": "human", "value": "Is the value of boy smaller than cell?" }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "Are the values in the chart presented in a percentage scale?" }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "What is the value of boy?" }, { "from": "gpt", "value": "40." }, { "from": "human", "value": "What is the label of the second bar from the left?" }, { "from": "gpt", "value": "Level." }, { "from": "human", "value": "Is each bar a single solid color without patterns?" }, { "from": "gpt", "value": "No." } ]
dvqa(cauldron,llava_format)
cauldron/dvqa/images/dvqa_00099582.png
[ { "from": "human", "value": "How many objects are preferred by less than 6 people in at least one category?\nAnswer the question using a single word or phrase." }, { "from": "gpt", "value": "Four." }, { "from": "human", "value": "Which object is preferred by the least number of people summed across all the categories?" }, { "from": "gpt", "value": "Pay." }, { "from": "human", "value": "Which object is preferred by the most number of people summed across all the categories?" }, { "from": "gpt", "value": "Tour." }, { "from": "human", "value": "How many total people preferred the object game across all the categories?" }, { "from": "gpt", "value": "22." }, { "from": "human", "value": "Is the object tour in the category bond preferred by more people than the object pay in the category center?" }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "What category does the forestgreen color represent?" }, { "from": "gpt", "value": "Spring." }, { "from": "human", "value": "How many people prefer the object pay in the category bond?" }, { "from": "gpt", "value": "2." }, { "from": "human", "value": "What is the label of the seventh stack of bars from the bottom?" }, { "from": "gpt", "value": "Actor." }, { "from": "human", "value": "What is the label of the first element from the left in each stack of bars?" }, { "from": "gpt", "value": "Bond." }, { "from": "human", "value": "Are the bars horizontal?" }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "Does the chart contain stacked bars?" }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "Is each bar a single solid color without patterns?" }, { "from": "gpt", "value": "No." } ]
dvqa(cauldron,llava_format)
cauldron/dvqa/images/dvqa_00099588.png
[ { "from": "human", "value": "How many groups of bars contain at least one bar with value greater than 10?\nAnswer the question using a single word or phrase." }, { "from": "gpt", "value": "Three." }, { "from": "human", "value": "Which group of bars contains the smallest valued individual bar in the whole chart?" }, { "from": "gpt", "value": "Lady." }, { "from": "human", "value": "What is the value of the smallest individual bar in the whole chart?" }, { "from": "gpt", "value": "10." }, { "from": "human", "value": "Which group has the smallest summed value?" }, { "from": "gpt", "value": "Lady." }, { "from": "human", "value": "Which group has the largest summed value?" }, { "from": "gpt", "value": "Tissue." }, { "from": "human", "value": "Is the value of tissue in man larger than the value of length in god?" }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "Are the values in the chart presented in a percentage scale?" }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "What element does the slateblue color represent?" }, { "from": "gpt", "value": "Band." }, { "from": "human", "value": "What is the value of random in lady?" }, { "from": "gpt", "value": "20." }, { "from": "human", "value": "What is the label of the third group of bars from the left?" }, { "from": "gpt", "value": "Lady." }, { "from": "human", "value": "What is the label of the second bar from the left in each group?" }, { "from": "gpt", "value": "God." }, { "from": "human", "value": "Does the chart contain stacked bars?" }, { "from": "gpt", "value": "No." } ]
dvqa(cauldron,llava_format)
cauldron/dvqa/images/dvqa_00099601.png
[ { "from": "human", "value": "How many algorithms have accuracy lower than 9 in at least one dataset?\nAnswer the question using a single word or phrase." }, { "from": "gpt", "value": "Five." }, { "from": "human", "value": "Which algorithm has lowest accuracy for any dataset?" }, { "from": "gpt", "value": "Date." }, { "from": "human", "value": "What is the lowest accuracy reported in the whole chart?" }, { "from": "gpt", "value": "1." }, { "from": "human", "value": "Which algorithm has the smallest accuracy summed across all the datasets?" }, { "from": "gpt", "value": "Date." }, { "from": "human", "value": "Which algorithm has the largest accuracy summed across all the datasets?" }, { "from": "gpt", "value": "Hole." }, { "from": "human", "value": "What is the sum of accuracies of the algorithm hole for all the datasets?" }, { "from": "gpt", "value": "18." }, { "from": "human", "value": "Are the values in the chart presented in a percentage scale?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "What is the accuracy of the algorithm coast in the dataset tube?" }, { "from": "gpt", "value": "6." }, { "from": "human", "value": "What is the label of the third stack of bars from the left?" }, { "from": "gpt", "value": "Sheet." }, { "from": "human", "value": "What is the label of the first element from the bottom in each stack of bars?" }, { "from": "gpt", "value": "Tone." }, { "from": "human", "value": "Does the chart contain stacked bars?" }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "How many elements are there in each stack of bars?" }, { "from": "gpt", "value": "Two." } ]
dvqa(cauldron,llava_format)
cauldron/dvqa/images/dvqa_00099602.png
[ { "from": "human", "value": "Which item sold the least units?\nAnswer the question using a single word or phrase." }, { "from": "gpt", "value": "Wire." }, { "from": "human", "value": "How many units of the the least sold item were sold?" }, { "from": "gpt", "value": "3." }, { "from": "human", "value": "How many items sold more than 9 units?" }, { "from": "gpt", "value": "Zero." }, { "from": "human", "value": "How many units of items person and wire were sold?" }, { "from": "gpt", "value": "12." }, { "from": "human", "value": "Did the item wire sold more units than spring?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "How many units of the item style were sold?" }, { "from": "gpt", "value": "9." }, { "from": "human", "value": "What is the label of the second bar from the bottom?" }, { "from": "gpt", "value": "Spring." }, { "from": "human", "value": "Are the bars horizontal?" }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "Is each bar a single solid color without patterns?" }, { "from": "gpt", "value": "Yes." } ]
dvqa(cauldron,llava_format)
cauldron/dvqa/images/dvqa_00099606.png
[ { "from": "human", "value": "Which bar has the largest value?\nAnswer the question using a single word or phrase." }, { "from": "gpt", "value": "Detail." }, { "from": "human", "value": "Which bar has the smallest value?" }, { "from": "gpt", "value": "Danger." }, { "from": "human", "value": "What is the value of the largest bar?" }, { "from": "gpt", "value": "50." }, { "from": "human", "value": "What is the value of the smallest bar?" }, { "from": "gpt", "value": "30." }, { "from": "human", "value": "What is the difference between the largest and the smallest value in the chart?" }, { "from": "gpt", "value": "20." }, { "from": "human", "value": "How many bars have values larger than 30?" }, { "from": "gpt", "value": "One." }, { "from": "human", "value": "Is the value of danger smaller than detail?" }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "Are the values in the chart presented in a percentage scale?" }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "What is the value of danger?" }, { "from": "gpt", "value": "30." }, { "from": "human", "value": "What is the label of the first bar from the left?" }, { "from": "gpt", "value": "Danger." }, { "from": "human", "value": "Are the bars horizontal?" }, { "from": "gpt", "value": "No." } ]
dvqa(cauldron,llava_format)
cauldron/dvqa/images/dvqa_00099614.png
[ { "from": "human", "value": "How many objects are preferred by less than 6 people in at least one category?\nAnswer the question using a single word or phrase." }, { "from": "gpt", "value": "Five." }, { "from": "human", "value": "Which object is the most preferred in any category?" }, { "from": "gpt", "value": "Period." }, { "from": "human", "value": "How many people like the most preferred object in the whole chart?" }, { "from": "gpt", "value": "8." }, { "from": "human", "value": "How many total people preferred the object flow across all the categories?" }, { "from": "gpt", "value": "6." }, { "from": "human", "value": "Is the object radio in the category inside preferred by more people than the object rush in the category march?" }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "What category does the forestgreen color represent?" }, { "from": "gpt", "value": "Inside." }, { "from": "human", "value": "How many people prefer the object guest in the category inside?" }, { "from": "gpt", "value": "6." }, { "from": "human", "value": "What is the label of the seventh group of bars from the bottom?" }, { "from": "gpt", "value": "Guest." }, { "from": "human", "value": "What is the label of the first bar from the bottom in each group?" }, { "from": "gpt", "value": "Inside." }, { "from": "human", "value": "Are the bars horizontal?" }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "Is each bar a single solid color without patterns?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "How many groups of bars are there?" }, { "from": "gpt", "value": "Seven." }, { "from": "human", "value": "How many bars are there per group?" }, { "from": "gpt", "value": "Two." } ]
dvqa(cauldron,llava_format)
cauldron/dvqa/images/dvqa_00099618.png
[ { "from": "human", "value": "Which bar has the largest value?\nAnswer the question using a single word or phrase." }, { "from": "gpt", "value": "Public." }, { "from": "human", "value": "What is the value of the largest bar?" }, { "from": "gpt", "value": "10000000." }, { "from": "human", "value": "How many bars have values larger than 10?" }, { "from": "gpt", "value": "Four." }, { "from": "human", "value": "Is the value of widow larger than excess?" }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "Are the values in the chart presented in a logarithmic scale?" }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "What is the value of writer?" }, { "from": "gpt", "value": "10." }, { "from": "human", "value": "What is the label of the first bar from the bottom?" }, { "from": "gpt", "value": "Course." }, { "from": "human", "value": "Are the bars horizontal?" }, { "from": "gpt", "value": "Yes." } ]
dvqa(cauldron,llava_format)
cauldron/dvqa/images/dvqa_00099630.png
[ { "from": "human", "value": "How many objects are preferred by less than 9 people in at least one category?\nAnswer the question using a single word or phrase." }, { "from": "gpt", "value": "Two." }, { "from": "human", "value": "Which object is the most preferred in any category?" }, { "from": "gpt", "value": "Cash." }, { "from": "human", "value": "Which object is the least preferred in any category?" }, { "from": "gpt", "value": "Cash." }, { "from": "human", "value": "How many people like the most preferred object in the whole chart?" }, { "from": "gpt", "value": "9." }, { "from": "human", "value": "How many people like the least preferred object in the whole chart?" }, { "from": "gpt", "value": "1." }, { "from": "human", "value": "Which object is preferred by the least number of people summed across all the categories?" }, { "from": "gpt", "value": "Root." }, { "from": "human", "value": "Which object is preferred by the most number of people summed across all the categories?" }, { "from": "gpt", "value": "Cash." }, { "from": "human", "value": "How many total people preferred the object cash across all the categories?" }, { "from": "gpt", "value": "19." }, { "from": "human", "value": "Is the object cash in the category money preferred by less people than the object root in the category gay?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "How many people prefer the object cash in the category gay?" }, { "from": "gpt", "value": "1." }, { "from": "human", "value": "What is the label of the first group of bars from the left?" }, { "from": "gpt", "value": "Root." }, { "from": "human", "value": "What is the label of the third bar from the left in each group?" }, { "from": "gpt", "value": "Money." } ]
dvqa(cauldron,llava_format)
cauldron/dvqa/images/dvqa_00099631.png
[ { "from": "human", "value": "How many algorithms have accuracy higher than 3 in at least one dataset?\nAnswer the question using a single word or phrase." }, { "from": "gpt", "value": "One." }, { "from": "human", "value": "Which algorithm has highest accuracy for any dataset?" }, { "from": "gpt", "value": "Love." }, { "from": "human", "value": "What is the highest accuracy reported in the whole chart?" }, { "from": "gpt", "value": "9." }, { "from": "human", "value": "Which algorithm has the smallest accuracy summed across all the datasets?" }, { "from": "gpt", "value": "Marine." }, { "from": "human", "value": "Which algorithm has the largest accuracy summed across all the datasets?" }, { "from": "gpt", "value": "Love." }, { "from": "human", "value": "What is the sum of accuracies of the algorithm path for all the datasets?" }, { "from": "gpt", "value": "4." }, { "from": "human", "value": "Is the accuracy of the algorithm love in the dataset value larger than the accuracy of the algorithm marine in the dataset field?" }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "What dataset does the palegoldenrod color represent?" }, { "from": "gpt", "value": "Field." }, { "from": "human", "value": "What is the accuracy of the algorithm path in the dataset field?" }, { "from": "gpt", "value": "3." }, { "from": "human", "value": "What is the label of the first group of bars from the bottom?" }, { "from": "gpt", "value": "Marine." }, { "from": "human", "value": "What is the label of the first bar from the bottom in each group?" }, { "from": "gpt", "value": "Value." }, { "from": "human", "value": "Are the bars horizontal?" }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "Is each bar a single solid color without patterns?" }, { "from": "gpt", "value": "Yes." } ]
dvqa(cauldron,llava_format)
cauldron/dvqa/images/dvqa_00099632.png
[ { "from": "human", "value": "How many algorithms have accuracy higher than 30 in at least one dataset?\nAnswer the question using a single word or phrase." }, { "from": "gpt", "value": "Five." }, { "from": "human", "value": "Which algorithm has the smallest accuracy summed across all the datasets?" }, { "from": "gpt", "value": "Angle." }, { "from": "human", "value": "Which algorithm has the largest accuracy summed across all the datasets?" }, { "from": "gpt", "value": "Bullet." }, { "from": "human", "value": "Is the accuracy of the algorithm talent in the dataset theory smaller than the accuracy of the algorithm bullet in the dataset realm?" }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "Are the values in the chart presented in a percentage scale?" }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "What dataset does the blue color represent?" }, { "from": "gpt", "value": "Realm." }, { "from": "human", "value": "What is the accuracy of the algorithm stroke in the dataset theory?" }, { "from": "gpt", "value": "40." }, { "from": "human", "value": "What is the label of the fourth group of bars from the left?" }, { "from": "gpt", "value": "Man." }, { "from": "human", "value": "What is the label of the third bar from the left in each group?" }, { "from": "gpt", "value": "Theory." }, { "from": "human", "value": "Are the bars horizontal?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "Is each bar a single solid color without patterns?" }, { "from": "gpt", "value": "Yes." } ]
dvqa(cauldron,llava_format)
cauldron/dvqa/images/dvqa_00099639.png
[ { "from": "human", "value": "Which algorithm has the highest accuracy?\nAnswer the question using a single word or phrase." }, { "from": "gpt", "value": "Boat." }, { "from": "human", "value": "Which algorithm has the lowest accuracy?" }, { "from": "gpt", "value": "Turn." }, { "from": "human", "value": "What is the accuracy of the algorithm with highest accuracy?" }, { "from": "gpt", "value": "9." }, { "from": "human", "value": "What is the accuracy of the algorithm with lowest accuracy?" }, { "from": "gpt", "value": "1." }, { "from": "human", "value": "How much more accurate is the most accurate algorithm compared the least accurate algorithm?" }, { "from": "gpt", "value": "8." }, { "from": "human", "value": "How many algorithms have accuracies higher than 9?" }, { "from": "gpt", "value": "Zero." }, { "from": "human", "value": "What is the sum of the accuracies of the algorithms pack and turn?" }, { "from": "gpt", "value": "4." }, { "from": "human", "value": "Is the accuracy of the algorithm moment smaller than boat?" }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "Are the values in the chart presented in a logarithmic scale?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "What is the accuracy of the algorithm moment?" }, { "from": "gpt", "value": "7." }, { "from": "human", "value": "What is the label of the third bar from the left?" }, { "from": "gpt", "value": "Boat." } ]
dvqa(cauldron,llava_format)
cauldron/dvqa/images/dvqa_00099640.png
[ { "from": "human", "value": "Which object is the most preferred?\nAnswer the question using a single word or phrase." }, { "from": "gpt", "value": "Gang." }, { "from": "human", "value": "Which object is the least preferred?" }, { "from": "gpt", "value": "Tent." }, { "from": "human", "value": "What percentage of people prefer the most preferred object?" }, { "from": "gpt", "value": "80." }, { "from": "human", "value": "What percentage of people prefer the least preferred object?" }, { "from": "gpt", "value": "40." }, { "from": "human", "value": "What is the difference between most and least preferred object?" }, { "from": "gpt", "value": "40." }, { "from": "human", "value": "How many objects are liked by more than 60 percent of people?" }, { "from": "gpt", "value": "One." }, { "from": "human", "value": "Is the object gang preferred by less people than bond?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "Are the values in the chart presented in a percentage scale?" }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "What percentage of people prefer the object bond?" }, { "from": "gpt", "value": "50." }, { "from": "human", "value": "What is the label of the fourth bar from the bottom?" }, { "from": "gpt", "value": "Way." }, { "from": "human", "value": "Are the bars horizontal?" }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "How many bars are there?" }, { "from": "gpt", "value": "Four." } ]
dvqa(cauldron,llava_format)
cauldron/dvqa/images/dvqa_00099642.png
[ { "from": "human", "value": "How many objects are preferred by less than 2 people in at least one category?\nAnswer the question using a single word or phrase." }, { "from": "gpt", "value": "Two." }, { "from": "human", "value": "Which object is the most preferred in any category?" }, { "from": "gpt", "value": "Seed." }, { "from": "human", "value": "How many people like the most preferred object in the whole chart?" }, { "from": "gpt", "value": "9." }, { "from": "human", "value": "Which object is preferred by the most number of people summed across all the categories?" }, { "from": "gpt", "value": "Seed." }, { "from": "human", "value": "How many total people preferred the object fence across all the categories?" }, { "from": "gpt", "value": "10." }, { "from": "human", "value": "Is the object value in the category cheek preferred by less people than the object vertex in the category card?" }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "What category does the steelblue color represent?" }, { "from": "gpt", "value": "Card." }, { "from": "human", "value": "How many people prefer the object vertex in the category card?" }, { "from": "gpt", "value": "6." }, { "from": "human", "value": "What is the label of the first group of bars from the left?" }, { "from": "gpt", "value": "Fence." }, { "from": "human", "value": "What is the label of the second bar from the left in each group?" }, { "from": "gpt", "value": "Cheek." }, { "from": "human", "value": "Is each bar a single solid color without patterns?" }, { "from": "gpt", "value": "No." } ]
dvqa(cauldron,llava_format)
cauldron/dvqa/images/dvqa_00099643.png
[ { "from": "human", "value": "How many items sold less than 5 units in at least one store?\nAnswer the question using a single word or phrase." }, { "from": "gpt", "value": "Seven." }, { "from": "human", "value": "Which item sold the least number of units summed across all the stores?" }, { "from": "gpt", "value": "Fish." }, { "from": "human", "value": "Which item sold the most number of units summed across all the stores?" }, { "from": "gpt", "value": "Race." }, { "from": "human", "value": "How many units of the item risk were sold across all the stores?" }, { "from": "gpt", "value": "13." }, { "from": "human", "value": "Did the item role in the store change sold smaller units than the item finger in the store paper?" }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "Are the values in the chart presented in a percentage scale?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "What store does the blue color represent?" }, { "from": "gpt", "value": "Change." }, { "from": "human", "value": "How many units of the item finger were sold in the store paper?" }, { "from": "gpt", "value": "9." }, { "from": "human", "value": "What is the label of the sixth stack of bars from the bottom?" }, { "from": "gpt", "value": "Store." }, { "from": "human", "value": "What is the label of the third element from the left in each stack of bars?" }, { "from": "gpt", "value": "Lie." }, { "from": "human", "value": "Are the bars horizontal?" }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "Does the chart contain stacked bars?" }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "Is each bar a single solid color without patterns?" }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "How many stacks of bars are there?" }, { "from": "gpt", "value": "Eight." } ]
dvqa(cauldron,llava_format)
cauldron/dvqa/images/dvqa_00099646.png
[ { "from": "human", "value": "How many groups of bars contain at least one bar with value smaller than 2?\nAnswer the question using a single word or phrase." }, { "from": "gpt", "value": "One." }, { "from": "human", "value": "Which group of bars contains the smallest valued individual bar in the whole chart?" }, { "from": "gpt", "value": "Self." }, { "from": "human", "value": "What is the value of the smallest individual bar in the whole chart?" }, { "from": "gpt", "value": "1." }, { "from": "human", "value": "Which group has the smallest summed value?" }, { "from": "gpt", "value": "Self." }, { "from": "human", "value": "Which group has the largest summed value?" }, { "from": "gpt", "value": "Memory." }, { "from": "human", "value": "What is the sum of all the values in the string group?" }, { "from": "gpt", "value": "11." }, { "from": "human", "value": "Is the value of doctor in roof smaller than the value of voting in area?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "What element does the steelblue color represent?" }, { "from": "gpt", "value": "Area." }, { "from": "human", "value": "What is the value of roof in self?" }, { "from": "gpt", "value": "2." }, { "from": "human", "value": "What is the label of the third group of bars from the left?" }, { "from": "gpt", "value": "Self." }, { "from": "human", "value": "What is the label of the first bar from the left in each group?" }, { "from": "gpt", "value": "Area." }, { "from": "human", "value": "Is each bar a single solid color without patterns?" }, { "from": "gpt", "value": "No." } ]
dvqa(cauldron,llava_format)
cauldron/dvqa/images/dvqa_00099654.png
[ { "from": "human", "value": "Which algorithm has the highest accuracy?\nAnswer the question using a single word or phrase." }, { "from": "gpt", "value": "Lack." }, { "from": "human", "value": "Which algorithm has the lowest accuracy?" }, { "from": "gpt", "value": "Form." }, { "from": "human", "value": "What is the accuracy of the algorithm with highest accuracy?" }, { "from": "gpt", "value": "7." }, { "from": "human", "value": "What is the accuracy of the algorithm with lowest accuracy?" }, { "from": "gpt", "value": "5." }, { "from": "human", "value": "How much more accurate is the most accurate algorithm compared the least accurate algorithm?" }, { "from": "gpt", "value": "2." }, { "from": "human", "value": "How many algorithms have accuracies higher than 5?" }, { "from": "gpt", "value": "Two." }, { "from": "human", "value": "What is the sum of the accuracies of the algorithms title and form?" }, { "from": "gpt", "value": "11." }, { "from": "human", "value": "Is the accuracy of the algorithm title smaller than lack?" }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "What is the accuracy of the algorithm lack?" }, { "from": "gpt", "value": "7." }, { "from": "human", "value": "What is the label of the second bar from the bottom?" }, { "from": "gpt", "value": "Lack." }, { "from": "human", "value": "Are the bars horizontal?" }, { "from": "gpt", "value": "Yes." } ]
dvqa(cauldron,llava_format)
cauldron/dvqa/images/dvqa_00099664.png
[ { "from": "human", "value": "How many algorithms have accuracy lower than 7 in at least one dataset?\nAnswer the question using a single word or phrase." }, { "from": "gpt", "value": "One." }, { "from": "human", "value": "Which algorithm has lowest accuracy for any dataset?" }, { "from": "gpt", "value": "Shame." }, { "from": "human", "value": "What is the lowest accuracy reported in the whole chart?" }, { "from": "gpt", "value": "1." }, { "from": "human", "value": "Which algorithm has the smallest accuracy summed across all the datasets?" }, { "from": "gpt", "value": "Shame." }, { "from": "human", "value": "Which algorithm has the largest accuracy summed across all the datasets?" }, { "from": "gpt", "value": "Pay." }, { "from": "human", "value": "What is the sum of accuracies of the algorithm shame for all the datasets?" }, { "from": "gpt", "value": "10." }, { "from": "human", "value": "Is the accuracy of the algorithm shame in the dataset slave smaller than the accuracy of the algorithm pay in the dataset deck?" }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "Are the values in the chart presented in a logarithmic scale?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "What dataset does the midnightblue color represent?" }, { "from": "gpt", "value": "Deck." }, { "from": "human", "value": "What is the accuracy of the algorithm shame in the dataset slave?" }, { "from": "gpt", "value": "1." }, { "from": "human", "value": "What is the label of the second group of bars from the left?" }, { "from": "gpt", "value": "Shame." }, { "from": "human", "value": "What is the label of the first bar from the left in each group?" }, { "from": "gpt", "value": "Deck." }, { "from": "human", "value": "Are the bars horizontal?" }, { "from": "gpt", "value": "No." } ]
dvqa(cauldron,llava_format)
cauldron/dvqa/images/dvqa_00099666.png
[ { "from": "human", "value": "How many groups of bars contain at least one bar with value smaller than 60?\nAnswer the question using a single word or phrase." }, { "from": "gpt", "value": "Two." }, { "from": "human", "value": "Which group has the smallest summed value?" }, { "from": "gpt", "value": "Stake." }, { "from": "human", "value": "Which group has the largest summed value?" }, { "from": "gpt", "value": "Mercy." }, { "from": "human", "value": "Is the value of worker in text smaller than the value of stake in random?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "Are the values in the chart presented in a percentage scale?" }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "What element does the steelblue color represent?" }, { "from": "gpt", "value": "Random." }, { "from": "human", "value": "What is the value of random in stake?" }, { "from": "gpt", "value": "70." }, { "from": "human", "value": "What is the label of the second group of bars from the left?" }, { "from": "gpt", "value": "Stake." }, { "from": "human", "value": "What is the label of the second bar from the left in each group?" }, { "from": "gpt", "value": "Random." }, { "from": "human", "value": "Does the chart contain any negative values?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "Are the bars horizontal?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "How many groups of bars are there?" }, { "from": "gpt", "value": "Three." } ]
dvqa(cauldron,llava_format)
cauldron/dvqa/images/dvqa_00099669.png
[ { "from": "human", "value": "Which algorithm has the highest accuracy?\nAnswer the question using a single word or phrase." }, { "from": "gpt", "value": "Secret." }, { "from": "human", "value": "Which algorithm has the lowest accuracy?" }, { "from": "gpt", "value": "Sewage." }, { "from": "human", "value": "What is the accuracy of the algorithm with highest accuracy?" }, { "from": "gpt", "value": "80." }, { "from": "human", "value": "What is the accuracy of the algorithm with lowest accuracy?" }, { "from": "gpt", "value": "30." }, { "from": "human", "value": "How much more accurate is the most accurate algorithm compared the least accurate algorithm?" }, { "from": "gpt", "value": "50." }, { "from": "human", "value": "How many algorithms have accuracies higher than 30?" }, { "from": "gpt", "value": "One." }, { "from": "human", "value": "Is the accuracy of the algorithm secret larger than sewage?" }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "Are the values in the chart presented in a percentage scale?" }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "What is the accuracy of the algorithm sewage?" }, { "from": "gpt", "value": "30." }, { "from": "human", "value": "What is the label of the second bar from the left?" }, { "from": "gpt", "value": "Sewage." } ]
dvqa(cauldron,llava_format)
cauldron/dvqa/images/dvqa_00099671.png
[ { "from": "human", "value": "How many groups of bars contain at least one bar with value smaller than 6?\nAnswer the question using a single word or phrase." }, { "from": "gpt", "value": "One." }, { "from": "human", "value": "Which group of bars contains the largest valued individual bar in the whole chart?" }, { "from": "gpt", "value": "Idea." }, { "from": "human", "value": "Which group of bars contains the smallest valued individual bar in the whole chart?" }, { "from": "gpt", "value": "Field." }, { "from": "human", "value": "What is the value of the largest individual bar in the whole chart?" }, { "from": "gpt", "value": "9." }, { "from": "human", "value": "What is the value of the smallest individual bar in the whole chart?" }, { "from": "gpt", "value": "4." }, { "from": "human", "value": "Which group has the smallest summed value?" }, { "from": "gpt", "value": "Field." }, { "from": "human", "value": "What is the sum of all the values in the air group?" }, { "from": "gpt", "value": "15." }, { "from": "human", "value": "Is the value of idea in show larger than the value of field in cold?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "What element does the royalblue color represent?" }, { "from": "gpt", "value": "Show." }, { "from": "human", "value": "What is the value of cold in excess?" }, { "from": "gpt", "value": "7." }, { "from": "human", "value": "What is the label of the third group of bars from the left?" }, { "from": "gpt", "value": "Field." }, { "from": "human", "value": "What is the label of the first bar from the left in each group?" }, { "from": "gpt", "value": "Show." }, { "from": "human", "value": "Is each bar a single solid color without patterns?" }, { "from": "gpt", "value": "No." } ]
dvqa(cauldron,llava_format)
cauldron/dvqa/images/dvqa_00099676.png
[ { "from": "human", "value": "How many objects are preferred by more than 1 people in at least one category?\nAnswer the question using a single word or phrase." }, { "from": "gpt", "value": "Seven." }, { "from": "human", "value": "Which object is the most preferred in any category?" }, { "from": "gpt", "value": "Food." }, { "from": "human", "value": "How many people like the most preferred object in the whole chart?" }, { "from": "gpt", "value": "9." }, { "from": "human", "value": "Which object is preferred by the least number of people summed across all the categories?" }, { "from": "gpt", "value": "Wine." }, { "from": "human", "value": "Which object is preferred by the most number of people summed across all the categories?" }, { "from": "gpt", "value": "Food." }, { "from": "human", "value": "How many total people preferred the object food across all the categories?" }, { "from": "gpt", "value": "22." }, { "from": "human", "value": "What category does the steelblue color represent?" }, { "from": "gpt", "value": "Relief." }, { "from": "human", "value": "How many people prefer the object fire in the category year?" }, { "from": "gpt", "value": "7." }, { "from": "human", "value": "What is the label of the second group of bars from the left?" }, { "from": "gpt", "value": "Wine." }, { "from": "human", "value": "What is the label of the third bar from the left in each group?" }, { "from": "gpt", "value": "Year." }, { "from": "human", "value": "Are the bars horizontal?" }, { "from": "gpt", "value": "No." } ]
dvqa(cauldron,llava_format)
cauldron/dvqa/images/dvqa_00099677.png
[ { "from": "human", "value": "How many groups of bars contain at least one bar with value smaller than 9?\nAnswer the question using a single word or phrase." }, { "from": "gpt", "value": "Three." }, { "from": "human", "value": "Which group has the smallest summed value?" }, { "from": "gpt", "value": "Data." }, { "from": "human", "value": "Which group has the largest summed value?" }, { "from": "gpt", "value": "Scene." }, { "from": "human", "value": "What is the sum of all the values in the ride group?" }, { "from": "gpt", "value": "10." }, { "from": "human", "value": "Is the value of ride in anode larger than the value of scene in player?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "Are the values in the chart presented in a percentage scale?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "What element does the darkorange color represent?" }, { "from": "gpt", "value": "Anode." }, { "from": "human", "value": "What is the value of anode in data?" }, { "from": "gpt", "value": "5." }, { "from": "human", "value": "What is the label of the fourth group of bars from the left?" }, { "from": "gpt", "value": "Scene." }, { "from": "human", "value": "What is the label of the first bar from the left in each group?" }, { "from": "gpt", "value": "Player." } ]
dvqa(cauldron,llava_format)
cauldron/dvqa/images/dvqa_00099681.png
[ { "from": "human", "value": "Which object is the most preferred?\nAnswer the question using a single word or phrase." }, { "from": "gpt", "value": "Device." }, { "from": "human", "value": "Which object is the least preferred?" }, { "from": "gpt", "value": "Color." }, { "from": "human", "value": "How many people prefer the most preferred object?" }, { "from": "gpt", "value": "8." }, { "from": "human", "value": "How many people prefer the least preferred object?" }, { "from": "gpt", "value": "1." }, { "from": "human", "value": "What is the difference between most and least preferred object?" }, { "from": "gpt", "value": "7." }, { "from": "human", "value": "How many objects are liked by more than 3 people?" }, { "from": "gpt", "value": "Two." }, { "from": "human", "value": "How many people prefer the objects iron or color?" }, { "from": "gpt", "value": "7." }, { "from": "human", "value": "Is the object device preferred by less people than iron?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "How many people prefer the object iron?" }, { "from": "gpt", "value": "6." }, { "from": "human", "value": "What is the label of the first bar from the bottom?" }, { "from": "gpt", "value": "Series." }, { "from": "human", "value": "Are the bars horizontal?" }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "Is each bar a single solid color without patterns?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "How many bars are there?" }, { "from": "gpt", "value": "Four." } ]
dvqa(cauldron,llava_format)
cauldron/dvqa/images/dvqa_00099686.png
[ { "from": "human", "value": "How many algorithms have accuracy higher than 6 in at least one dataset?\nAnswer the question using a single word or phrase." }, { "from": "gpt", "value": "Six." }, { "from": "human", "value": "Which algorithm has the smallest accuracy summed across all the datasets?" }, { "from": "gpt", "value": "Fire." }, { "from": "human", "value": "Which algorithm has the largest accuracy summed across all the datasets?" }, { "from": "gpt", "value": "Valley." }, { "from": "human", "value": "What is the sum of accuracies of the algorithm fire for all the datasets?" }, { "from": "gpt", "value": "10." }, { "from": "human", "value": "Is the accuracy of the algorithm cash in the dataset floor larger than the accuracy of the algorithm land in the dataset flood?" }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "Are the values in the chart presented in a percentage scale?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "What dataset does the darkorange color represent?" }, { "from": "gpt", "value": "Grip." }, { "from": "human", "value": "What is the accuracy of the algorithm wound in the dataset grip?" }, { "from": "gpt", "value": "9." }, { "from": "human", "value": "What is the label of the third group of bars from the left?" }, { "from": "gpt", "value": "Cash." }, { "from": "human", "value": "What is the label of the first bar from the left in each group?" }, { "from": "gpt", "value": "Flood." }, { "from": "human", "value": "Is each bar a single solid color without patterns?" }, { "from": "gpt", "value": "No." } ]
dvqa(cauldron,llava_format)
cauldron/dvqa/images/dvqa_00099688.png
[ { "from": "human", "value": "Which algorithm has the highest accuracy?\nAnswer the question using a single word or phrase." }, { "from": "gpt", "value": "Forth." }, { "from": "human", "value": "Which algorithm has the lowest accuracy?" }, { "from": "gpt", "value": "Seed." }, { "from": "human", "value": "What is the accuracy of the algorithm with highest accuracy?" }, { "from": "gpt", "value": "7." }, { "from": "human", "value": "What is the accuracy of the algorithm with lowest accuracy?" }, { "from": "gpt", "value": "5." }, { "from": "human", "value": "How much more accurate is the most accurate algorithm compared the least accurate algorithm?" }, { "from": "gpt", "value": "2." }, { "from": "human", "value": "How many algorithms have accuracies higher than 5?" }, { "from": "gpt", "value": "Two." }, { "from": "human", "value": "What is the sum of the accuracies of the algorithms neck and forth?" }, { "from": "gpt", "value": "13." }, { "from": "human", "value": "Is the accuracy of the algorithm neck smaller than seed?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "What is the accuracy of the algorithm seed?" }, { "from": "gpt", "value": "5." }, { "from": "human", "value": "What is the label of the second bar from the left?" }, { "from": "gpt", "value": "Neck." }, { "from": "human", "value": "Does the chart contain stacked bars?" }, { "from": "gpt", "value": "No." } ]
dvqa(cauldron,llava_format)
cauldron/dvqa/images/dvqa_00099692.png
[ { "from": "human", "value": "How many objects are preferred by less than 8 people in at least one category?\nAnswer the question using a single word or phrase." }, { "from": "gpt", "value": "Three." }, { "from": "human", "value": "Which object is the most preferred in any category?" }, { "from": "gpt", "value": "Bond." }, { "from": "human", "value": "How many people like the most preferred object in the whole chart?" }, { "from": "gpt", "value": "8." }, { "from": "human", "value": "Which object is preferred by the most number of people summed across all the categories?" }, { "from": "gpt", "value": "Bond." }, { "from": "human", "value": "How many total people preferred the object bond across all the categories?" }, { "from": "gpt", "value": "13." }, { "from": "human", "value": "What category does the crimson color represent?" }, { "from": "gpt", "value": "Anode." }, { "from": "human", "value": "How many people prefer the object bond in the category track?" }, { "from": "gpt", "value": "8." }, { "from": "human", "value": "What is the label of the first group of bars from the left?" }, { "from": "gpt", "value": "Bond." }, { "from": "human", "value": "What is the label of the first bar from the left in each group?" }, { "from": "gpt", "value": "Track." }, { "from": "human", "value": "Are the bars horizontal?" }, { "from": "gpt", "value": "No." } ]
dvqa(cauldron,llava_format)
cauldron/dvqa/images/dvqa_00099695.png
[ { "from": "human", "value": "Which object is the most preferred?\nAnswer the question using a single word or phrase." }, { "from": "gpt", "value": "Hold." }, { "from": "human", "value": "Which object is the least preferred?" }, { "from": "gpt", "value": "Grave." }, { "from": "human", "value": "How many people prefer the most preferred object?" }, { "from": "gpt", "value": "8." }, { "from": "human", "value": "How many people prefer the least preferred object?" }, { "from": "gpt", "value": "3." }, { "from": "human", "value": "What is the difference between most and least preferred object?" }, { "from": "gpt", "value": "5." }, { "from": "human", "value": "How many objects are liked by less than 6 people?" }, { "from": "gpt", "value": "Two." }, { "from": "human", "value": "How many people prefer the objects grave or image?" }, { "from": "gpt", "value": "9." }, { "from": "human", "value": "Is the object grave preferred by less people than image?" }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "How many people prefer the object sewage?" }, { "from": "gpt", "value": "4." }, { "from": "human", "value": "What is the label of the second bar from the left?" }, { "from": "gpt", "value": "Hold." }, { "from": "human", "value": "Are the bars horizontal?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "Does the chart contain stacked bars?" }, { "from": "gpt", "value": "No." } ]
dvqa(cauldron,llava_format)
cauldron/dvqa/images/dvqa_00099696.png
[ { "from": "human", "value": "Which algorithm has the highest accuracy?\nAnswer the question using a single word or phrase." }, { "from": "gpt", "value": "Lawyer." }, { "from": "human", "value": "Which algorithm has the lowest accuracy?" }, { "from": "gpt", "value": "Class." }, { "from": "human", "value": "What is the accuracy of the algorithm with highest accuracy?" }, { "from": "gpt", "value": "8." }, { "from": "human", "value": "What is the accuracy of the algorithm with lowest accuracy?" }, { "from": "gpt", "value": "5." }, { "from": "human", "value": "How much more accurate is the most accurate algorithm compared the least accurate algorithm?" }, { "from": "gpt", "value": "3." }, { "from": "human", "value": "How many algorithms have accuracies higher than 8?" }, { "from": "gpt", "value": "Zero." }, { "from": "human", "value": "What is the sum of the accuracies of the algorithms class and lawyer?" }, { "from": "gpt", "value": "13." }, { "from": "human", "value": "Is the accuracy of the algorithm class larger than lawyer?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "Are the values in the chart presented in a logarithmic scale?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "Are the values in the chart presented in a percentage scale?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "What is the accuracy of the algorithm lawyer?" }, { "from": "gpt", "value": "8." }, { "from": "human", "value": "What is the label of the second bar from the left?" }, { "from": "gpt", "value": "Class." }, { "from": "human", "value": "Are the bars horizontal?" }, { "from": "gpt", "value": "No." } ]
dvqa(cauldron,llava_format)
cauldron/dvqa/images/dvqa_00099700.png
[ { "from": "human", "value": "Which algorithm has the highest accuracy?\nAnswer the question using a single word or phrase." }, { "from": "gpt", "value": "Column." }, { "from": "human", "value": "Which algorithm has the lowest accuracy?" }, { "from": "gpt", "value": "Class." }, { "from": "human", "value": "What is the accuracy of the algorithm with highest accuracy?" }, { "from": "gpt", "value": "9." }, { "from": "human", "value": "What is the accuracy of the algorithm with lowest accuracy?" }, { "from": "gpt", "value": "1." }, { "from": "human", "value": "How much more accurate is the most accurate algorithm compared the least accurate algorithm?" }, { "from": "gpt", "value": "8." }, { "from": "human", "value": "How many algorithms have accuracies higher than 1?" }, { "from": "gpt", "value": "Five." }, { "from": "human", "value": "What is the sum of the accuracies of the algorithms gyro and class?" }, { "from": "gpt", "value": "6." }, { "from": "human", "value": "Is the accuracy of the algorithm class larger than faint?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "Are the values in the chart presented in a percentage scale?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "What is the accuracy of the algorithm gyro?" }, { "from": "gpt", "value": "5." }, { "from": "human", "value": "What is the label of the first bar from the left?" }, { "from": "gpt", "value": "Faint." }, { "from": "human", "value": "How many bars are there?" }, { "from": "gpt", "value": "Six." } ]
dvqa(cauldron,llava_format)
cauldron/dvqa/images/dvqa_00099702.png
[ { "from": "human", "value": "How many algorithms have accuracy lower than 7 in at least one dataset?\nAnswer the question using a single word or phrase." }, { "from": "gpt", "value": "Two." }, { "from": "human", "value": "Which algorithm has lowest accuracy for any dataset?" }, { "from": "gpt", "value": "Stay." }, { "from": "human", "value": "What is the lowest accuracy reported in the whole chart?" }, { "from": "gpt", "value": "2." }, { "from": "human", "value": "Which algorithm has the smallest accuracy summed across all the datasets?" }, { "from": "gpt", "value": "Stay." }, { "from": "human", "value": "Which algorithm has the largest accuracy summed across all the datasets?" }, { "from": "gpt", "value": "Curve." }, { "from": "human", "value": "What is the sum of accuracies of the algorithm stay for all the datasets?" }, { "from": "gpt", "value": "12." }, { "from": "human", "value": "Is the accuracy of the algorithm stay in the dataset behalf larger than the accuracy of the algorithm curve in the dataset panic?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "Are the values in the chart presented in a percentage scale?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "What dataset does the chocolate color represent?" }, { "from": "gpt", "value": "Behalf." }, { "from": "human", "value": "What is the accuracy of the algorithm curve in the dataset panic?" }, { "from": "gpt", "value": "7." }, { "from": "human", "value": "What is the label of the second group of bars from the left?" }, { "from": "gpt", "value": "Stay." }, { "from": "human", "value": "What is the label of the second bar from the left in each group?" }, { "from": "gpt", "value": "Plain." } ]
dvqa(cauldron,llava_format)
cauldron/dvqa/images/dvqa_00099704.png
[ { "from": "human", "value": "How many bars have values larger than 100000000?\nAnswer the question using a single word or phrase." }, { "from": "gpt", "value": "Zero." }, { "from": "human", "value": "Is the value of knife smaller than army?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "Are the values in the chart presented in a logarithmic scale?" }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "What is the value of grass?" }, { "from": "gpt", "value": "10." }, { "from": "human", "value": "What is the label of the first bar from the left?" }, { "from": "gpt", "value": "Army." }, { "from": "human", "value": "Is each bar a single solid color without patterns?" }, { "from": "gpt", "value": "No." } ]
dvqa(cauldron,llava_format)
cauldron/dvqa/images/dvqa_00099709.png
[ { "from": "human", "value": "How many groups of bars contain at least one bar with value smaller than 8?\nAnswer the question using a single word or phrase." }, { "from": "gpt", "value": "Seven." }, { "from": "human", "value": "Which group of bars contains the smallest valued individual bar in the whole chart?" }, { "from": "gpt", "value": "Track." }, { "from": "human", "value": "What is the value of the smallest individual bar in the whole chart?" }, { "from": "gpt", "value": "-9." }, { "from": "human", "value": "Which group has the smallest summed value?" }, { "from": "gpt", "value": "Track." }, { "from": "human", "value": "Which group has the largest summed value?" }, { "from": "gpt", "value": "Style." }, { "from": "human", "value": "Is the value of year in fate smaller than the value of post in fight?" }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "What element does the gold color represent?" }, { "from": "gpt", "value": "Fight." }, { "from": "human", "value": "What is the value of fight in year?" }, { "from": "gpt", "value": "1." }, { "from": "human", "value": "What is the label of the first group of bars from the left?" }, { "from": "gpt", "value": "Track." }, { "from": "human", "value": "What is the label of the second bar from the left in each group?" }, { "from": "gpt", "value": "Fight." }, { "from": "human", "value": "Does the chart contain any negative values?" }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "Are the bars horizontal?" }, { "from": "gpt", "value": "No." } ]
dvqa(cauldron,llava_format)
cauldron/dvqa/images/dvqa_00099712.png
[ { "from": "human", "value": "Which algorithm has the highest accuracy?\nAnswer the question using a single word or phrase." }, { "from": "gpt", "value": "Judge." }, { "from": "human", "value": "Which algorithm has the lowest accuracy?" }, { "from": "gpt", "value": "Lay." }, { "from": "human", "value": "What is the accuracy of the algorithm with highest accuracy?" }, { "from": "gpt", "value": "90." }, { "from": "human", "value": "What is the accuracy of the algorithm with lowest accuracy?" }, { "from": "gpt", "value": "60." }, { "from": "human", "value": "How much more accurate is the most accurate algorithm compared the least accurate algorithm?" }, { "from": "gpt", "value": "30." }, { "from": "human", "value": "How many algorithms have accuracies lower than 60?" }, { "from": "gpt", "value": "Zero." }, { "from": "human", "value": "Is the accuracy of the algorithm judge smaller than sport?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "Are the values in the chart presented in a percentage scale?" }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "What is the accuracy of the algorithm judge?" }, { "from": "gpt", "value": "90." }, { "from": "human", "value": "What is the label of the second bar from the left?" }, { "from": "gpt", "value": "Judge." } ]
dvqa(cauldron,llava_format)
cauldron/dvqa/images/dvqa_00099717.png
[ { "from": "human", "value": "How many objects are preferred by less than 20 percent of people in at least one category?\nAnswer the question using a single word or phrase." }, { "from": "gpt", "value": "One." }, { "from": "human", "value": "Which object is the most preferred in any category?" }, { "from": "gpt", "value": "Plant." }, { "from": "human", "value": "Which object is the least preferred in any category?" }, { "from": "gpt", "value": "Comedy." }, { "from": "human", "value": "What percentage of people like the most preferred object in the whole chart?" }, { "from": "gpt", "value": "50." }, { "from": "human", "value": "What percentage of people like the least preferred object in the whole chart?" }, { "from": "gpt", "value": "10." }, { "from": "human", "value": "Which object is preferred by the most number of people summed across all the categories?" }, { "from": "gpt", "value": "Rifle." }, { "from": "human", "value": "Is the value of plant in coal smaller than the value of medium in peace?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "Are the values in the chart presented in a percentage scale?" }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "What category does the darkorange color represent?" }, { "from": "gpt", "value": "Peace." }, { "from": "human", "value": "What percentage of people prefer the object plant in the category peace?" }, { "from": "gpt", "value": "20." }, { "from": "human", "value": "What is the label of the second group of bars from the left?" }, { "from": "gpt", "value": "Rifle." }, { "from": "human", "value": "What is the label of the first bar from the left in each group?" }, { "from": "gpt", "value": "Coal." } ]
dvqa(cauldron,llava_format)
cauldron/dvqa/images/dvqa_00099718.png
[ { "from": "human", "value": "Which item sold the most units?\nAnswer the question using a single word or phrase." }, { "from": "gpt", "value": "Pride." }, { "from": "human", "value": "Which item sold the least units?" }, { "from": "gpt", "value": "Park." }, { "from": "human", "value": "How many units of the the most sold item were sold?" }, { "from": "gpt", "value": "9." }, { "from": "human", "value": "How many units of the the least sold item were sold?" }, { "from": "gpt", "value": "1." }, { "from": "human", "value": "How many more of the most sold item were sold compared to the least sold item?" }, { "from": "gpt", "value": "8." }, { "from": "human", "value": "How many items sold less than 4 units?" }, { "from": "gpt", "value": "One." }, { "from": "human", "value": "How many units of items escape and brain were sold?" }, { "from": "gpt", "value": "12." }, { "from": "human", "value": "How many units of the item phase were sold?" }, { "from": "gpt", "value": "5." }, { "from": "human", "value": "What is the label of the fourth bar from the left?" }, { "from": "gpt", "value": "Phase." }, { "from": "human", "value": "Is each bar a single solid color without patterns?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "How many bars are there?" }, { "from": "gpt", "value": "Eight." } ]
dvqa(cauldron,llava_format)
cauldron/dvqa/images/dvqa_00099720.png
[ { "from": "human", "value": "How many objects are preferred by less than 4 people in at least one category?\nAnswer the question using a single word or phrase." }, { "from": "gpt", "value": "Two." }, { "from": "human", "value": "Which object is the least preferred in any category?" }, { "from": "gpt", "value": "Thick." }, { "from": "human", "value": "How many people like the least preferred object in the whole chart?" }, { "from": "gpt", "value": "1." }, { "from": "human", "value": "Which object is preferred by the least number of people summed across all the categories?" }, { "from": "gpt", "value": "Thick." }, { "from": "human", "value": "Which object is preferred by the most number of people summed across all the categories?" }, { "from": "gpt", "value": "Bill." }, { "from": "human", "value": "How many total people preferred the object thick across all the categories?" }, { "from": "gpt", "value": "19." }, { "from": "human", "value": "Is the object bill in the category wire preferred by less people than the object thick in the category house?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "What category does the blue color represent?" }, { "from": "gpt", "value": "Virtue." }, { "from": "human", "value": "How many people prefer the object hill in the category house?" }, { "from": "gpt", "value": "8." }, { "from": "human", "value": "What is the label of the first group of bars from the left?" }, { "from": "gpt", "value": "Hill." }, { "from": "human", "value": "What is the label of the fourth bar from the left in each group?" }, { "from": "gpt", "value": "House." }, { "from": "human", "value": "Does the chart contain any negative values?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "Are the bars horizontal?" }, { "from": "gpt", "value": "No." } ]
dvqa(cauldron,llava_format)
cauldron/dvqa/images/dvqa_00099725.png
[ { "from": "human", "value": "How many algorithms have accuracy higher than 80 in at least one dataset?\nAnswer the question using a single word or phrase." }, { "from": "gpt", "value": "Zero." }, { "from": "human", "value": "Which algorithm has lowest accuracy for any dataset?" }, { "from": "gpt", "value": "Point." }, { "from": "human", "value": "What is the lowest accuracy reported in the whole chart?" }, { "from": "gpt", "value": "10." }, { "from": "human", "value": "Which algorithm has the smallest accuracy summed across all the datasets?" }, { "from": "gpt", "value": "Word." }, { "from": "human", "value": "Which algorithm has the largest accuracy summed across all the datasets?" }, { "from": "gpt", "value": "Flow." }, { "from": "human", "value": "Is the accuracy of the algorithm flow in the dataset fight smaller than the accuracy of the algorithm word in the dataset dark?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "Are the values in the chart presented in a logarithmic scale?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "Are the values in the chart presented in a percentage scale?" }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "What dataset does the steelblue color represent?" }, { "from": "gpt", "value": "Dark." }, { "from": "human", "value": "What is the accuracy of the algorithm flow in the dataset dark?" }, { "from": "gpt", "value": "70." }, { "from": "human", "value": "What is the label of the fifth group of bars from the bottom?" }, { "from": "gpt", "value": "Birth." }, { "from": "human", "value": "What is the label of the second bar from the bottom in each group?" }, { "from": "gpt", "value": "Fight." }, { "from": "human", "value": "Are the bars horizontal?" }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "Is each bar a single solid color without patterns?" }, { "from": "gpt", "value": "Yes." } ]
dvqa(cauldron,llava_format)
cauldron/dvqa/images/dvqa_00099726.png
[ { "from": "human", "value": "Which bar has the smallest value?\nAnswer the question using a single word or phrase." }, { "from": "gpt", "value": "Answer." }, { "from": "human", "value": "What is the value of the smallest bar?" }, { "from": "gpt", "value": "1000." }, { "from": "human", "value": "How many bars have values larger than 1000?" }, { "from": "gpt", "value": "Two." }, { "from": "human", "value": "Are the values in the chart presented in a logarithmic scale?" }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "What is the value of stone?" }, { "from": "gpt", "value": "1000000." }, { "from": "human", "value": "What is the label of the third bar from the bottom?" }, { "from": "gpt", "value": "Answer." }, { "from": "human", "value": "Are the bars horizontal?" }, { "from": "gpt", "value": "Yes." } ]
dvqa(cauldron,llava_format)
cauldron/dvqa/images/dvqa_00099731.png
[ { "from": "human", "value": "Which algorithm has the highest accuracy?\nAnswer the question using a single word or phrase." }, { "from": "gpt", "value": "Task." }, { "from": "human", "value": "Which algorithm has the lowest accuracy?" }, { "from": "gpt", "value": "Volume." }, { "from": "human", "value": "What is the accuracy of the algorithm with highest accuracy?" }, { "from": "gpt", "value": "9." }, { "from": "human", "value": "What is the accuracy of the algorithm with lowest accuracy?" }, { "from": "gpt", "value": "1." }, { "from": "human", "value": "How much more accurate is the most accurate algorithm compared the least accurate algorithm?" }, { "from": "gpt", "value": "8." }, { "from": "human", "value": "How many algorithms have accuracies lower than 3?" }, { "from": "gpt", "value": "Two." }, { "from": "human", "value": "What is the sum of the accuracies of the algorithms horror and volume?" }, { "from": "gpt", "value": "3." }, { "from": "human", "value": "Is the accuracy of the algorithm strike larger than fruit?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "Are the values in the chart presented in a percentage scale?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "What is the accuracy of the algorithm task?" }, { "from": "gpt", "value": "9." }, { "from": "human", "value": "What is the label of the first bar from the left?" }, { "from": "gpt", "value": "Strike." } ]
dvqa(cauldron,llava_format)
cauldron/dvqa/images/dvqa_00099734.png
[ { "from": "human", "value": "How many groups of bars contain at least one bar with value smaller than 3?\nAnswer the question using a single word or phrase." }, { "from": "gpt", "value": "One." }, { "from": "human", "value": "Which group of bars contains the smallest valued individual bar in the whole chart?" }, { "from": "gpt", "value": "Whisky." }, { "from": "human", "value": "What is the value of the smallest individual bar in the whole chart?" }, { "from": "gpt", "value": "2." }, { "from": "human", "value": "Which group has the largest summed value?" }, { "from": "gpt", "value": "Heart." }, { "from": "human", "value": "What is the sum of all the values in the child group?" }, { "from": "gpt", "value": "11." }, { "from": "human", "value": "Is the value of whisky in damage smaller than the value of gang in volume?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "Are the values in the chart presented in a percentage scale?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "What element does the darkorange color represent?" }, { "from": "gpt", "value": "Volume." }, { "from": "human", "value": "What is the value of volume in child?" }, { "from": "gpt", "value": "3." }, { "from": "human", "value": "What is the label of the second group of bars from the left?" }, { "from": "gpt", "value": "Gang." }, { "from": "human", "value": "What is the label of the first bar from the left in each group?" }, { "from": "gpt", "value": "Damage." } ]
dvqa(cauldron,llava_format)
cauldron/dvqa/images/dvqa_00099741.png
[ { "from": "human", "value": "Which algorithm has the highest accuracy?\nAnswer the question using a single word or phrase." }, { "from": "gpt", "value": "Entry." }, { "from": "human", "value": "Which algorithm has the lowest accuracy?" }, { "from": "gpt", "value": "One." }, { "from": "human", "value": "What is the accuracy of the algorithm with highest accuracy?" }, { "from": "gpt", "value": "7." }, { "from": "human", "value": "What is the accuracy of the algorithm with lowest accuracy?" }, { "from": "gpt", "value": "1." }, { "from": "human", "value": "How much more accurate is the most accurate algorithm compared the least accurate algorithm?" }, { "from": "gpt", "value": "6." }, { "from": "human", "value": "How many algorithms have accuracies lower than 2?" }, { "from": "gpt", "value": "One." }, { "from": "human", "value": "What is the sum of the accuracies of the algorithms man and entry?" }, { "from": "gpt", "value": "13." }, { "from": "human", "value": "Is the accuracy of the algorithm one smaller than man?" }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "Are the values in the chart presented in a logarithmic scale?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "What is the accuracy of the algorithm entry?" }, { "from": "gpt", "value": "7." }, { "from": "human", "value": "What is the label of the fourth bar from the left?" }, { "from": "gpt", "value": "Man." }, { "from": "human", "value": "How many bars are there?" }, { "from": "gpt", "value": "Five." } ]
dvqa(cauldron,llava_format)
cauldron/dvqa/images/dvqa_00099746.png
[ { "from": "human", "value": "How many items sold less than 2 units in at least one store?\nAnswer the question using a single word or phrase." }, { "from": "gpt", "value": "One." }, { "from": "human", "value": "Which item sold the least units in any shop?" }, { "from": "gpt", "value": "Stand." }, { "from": "human", "value": "How many units did the worst selling item sell in the whole chart?" }, { "from": "gpt", "value": "1." }, { "from": "human", "value": "Which item sold the least number of units summed across all the stores?" }, { "from": "gpt", "value": "Stand." }, { "from": "human", "value": "Which item sold the most number of units summed across all the stores?" }, { "from": "gpt", "value": "Fee." }, { "from": "human", "value": "How many units of the item kind were sold across all the stores?" }, { "from": "gpt", "value": "10." }, { "from": "human", "value": "Did the item kind in the store hay sold smaller units than the item focus in the store square?" }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "Are the values in the chart presented in a percentage scale?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "What store does the red color represent?" }, { "from": "gpt", "value": "Square." }, { "from": "human", "value": "How many units of the item stand were sold in the store hay?" }, { "from": "gpt", "value": "1." }, { "from": "human", "value": "What is the label of the second group of bars from the left?" }, { "from": "gpt", "value": "Stand." }, { "from": "human", "value": "What is the label of the second bar from the left in each group?" }, { "from": "gpt", "value": "Hay." }, { "from": "human", "value": "Is each bar a single solid color without patterns?" }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "How many groups of bars are there?" }, { "from": "gpt", "value": "Nine." } ]
dvqa(cauldron,llava_format)
cauldron/dvqa/images/dvqa_00099750.png
[ { "from": "human", "value": "How many groups of bars contain at least one bar with value smaller than 80?\nAnswer the question using a single word or phrase." }, { "from": "gpt", "value": "Four." }, { "from": "human", "value": "Which group of bars contains the largest valued individual bar in the whole chart?" }, { "from": "gpt", "value": "Form." }, { "from": "human", "value": "What is the value of the largest individual bar in the whole chart?" }, { "from": "gpt", "value": "90." }, { "from": "human", "value": "Which group has the smallest summed value?" }, { "from": "gpt", "value": "Crime." }, { "from": "human", "value": "Is the value of form in floor smaller than the value of slave in bride?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "Are the values in the chart presented in a percentage scale?" }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "What element does the darkorange color represent?" }, { "from": "gpt", "value": "Floor." }, { "from": "human", "value": "What is the value of child in slave?" }, { "from": "gpt", "value": "80." }, { "from": "human", "value": "What is the label of the second group of bars from the left?" }, { "from": "gpt", "value": "Form." }, { "from": "human", "value": "What is the label of the first bar from the left in each group?" }, { "from": "gpt", "value": "Child." }, { "from": "human", "value": "How many groups of bars are there?" }, { "from": "gpt", "value": "Four." } ]
dvqa(cauldron,llava_format)
cauldron/dvqa/images/dvqa_00099751.png
[ { "from": "human", "value": "Which item sold the most units?\nAnswer the question using a single word or phrase." }, { "from": "gpt", "value": "Melody." }, { "from": "human", "value": "How many units of the the most sold item were sold?" }, { "from": "gpt", "value": "8." }, { "from": "human", "value": "How many items sold more than 5 units?" }, { "from": "gpt", "value": "Three." }, { "from": "human", "value": "How many units of items lip and winter were sold?" }, { "from": "gpt", "value": "4." }, { "from": "human", "value": "Did the item walk sold more units than handle?" }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "Are the values in the chart presented in a percentage scale?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "How many units of the item cannot were sold?" }, { "from": "gpt", "value": "5." }, { "from": "human", "value": "What is the label of the eighth bar from the left?" }, { "from": "gpt", "value": "Wheel." }, { "from": "human", "value": "Does the chart contain any negative values?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "How many bars are there?" }, { "from": "gpt", "value": "Eight." } ]
dvqa(cauldron,llava_format)
cauldron/dvqa/images/dvqa_00099752.png
[ { "from": "human", "value": "How many objects are preferred by more than 10 percent of people in at least one category?\nAnswer the question using a single word or phrase." }, { "from": "gpt", "value": "Four." }, { "from": "human", "value": "Which object is preferred by the least number of people summed across all the categories?" }, { "from": "gpt", "value": "Search." }, { "from": "human", "value": "Which object is preferred by the most number of people summed across all the categories?" }, { "from": "gpt", "value": "Closet." }, { "from": "human", "value": "Is the value of pink in tray smaller than the value of gain in house?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "Are the values in the chart presented in a logarithmic scale?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "Are the values in the chart presented in a percentage scale?" }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "What category does the deepskyblue color represent?" }, { "from": "gpt", "value": "House." }, { "from": "human", "value": "What percentage of people prefer the object closet in the category body?" }, { "from": "gpt", "value": "90." }, { "from": "human", "value": "What is the label of the first group of bars from the left?" }, { "from": "gpt", "value": "Closet." }, { "from": "human", "value": "What is the label of the fourth bar from the left in each group?" }, { "from": "gpt", "value": "House." }, { "from": "human", "value": "Is each bar a single solid color without patterns?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "How many bars are there per group?" }, { "from": "gpt", "value": "Four." } ]
dvqa(cauldron,llava_format)
cauldron/dvqa/images/dvqa_00099761.png
[ { "from": "human", "value": "Which algorithm has the highest accuracy?\nAnswer the question using a single word or phrase." }, { "from": "gpt", "value": "Wire." }, { "from": "human", "value": "Which algorithm has the lowest accuracy?" }, { "from": "gpt", "value": "Auto." }, { "from": "human", "value": "What is the accuracy of the algorithm with highest accuracy?" }, { "from": "gpt", "value": "8." }, { "from": "human", "value": "What is the accuracy of the algorithm with lowest accuracy?" }, { "from": "gpt", "value": "1." }, { "from": "human", "value": "How much more accurate is the most accurate algorithm compared the least accurate algorithm?" }, { "from": "gpt", "value": "7." }, { "from": "human", "value": "How many algorithms have accuracies higher than 2?" }, { "from": "gpt", "value": "Three." }, { "from": "human", "value": "What is the sum of the accuracies of the algorithms auto and inch?" }, { "from": "gpt", "value": "4." }, { "from": "human", "value": "Is the accuracy of the algorithm credit smaller than wire?" }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "What is the accuracy of the algorithm auto?" }, { "from": "gpt", "value": "1." }, { "from": "human", "value": "What is the label of the first bar from the left?" }, { "from": "gpt", "value": "Inch." }, { "from": "human", "value": "Does the chart contain stacked bars?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "Is each bar a single solid color without patterns?" }, { "from": "gpt", "value": "No." } ]
dvqa(cauldron,llava_format)
cauldron/dvqa/images/dvqa_00099764.png
[ { "from": "human", "value": "Which algorithm has the highest accuracy?\nAnswer the question using a single word or phrase." }, { "from": "gpt", "value": "Dome." }, { "from": "human", "value": "Which algorithm has the lowest accuracy?" }, { "from": "gpt", "value": "Ride." }, { "from": "human", "value": "What is the accuracy of the algorithm with highest accuracy?" }, { "from": "gpt", "value": "8." }, { "from": "human", "value": "What is the accuracy of the algorithm with lowest accuracy?" }, { "from": "gpt", "value": "4." }, { "from": "human", "value": "How much more accurate is the most accurate algorithm compared the least accurate algorithm?" }, { "from": "gpt", "value": "4." }, { "from": "human", "value": "How many algorithms have accuracies lower than 7?" }, { "from": "gpt", "value": "Three." }, { "from": "human", "value": "What is the sum of the accuracies of the algorithms cellar and burden?" }, { "from": "gpt", "value": "12." }, { "from": "human", "value": "Is the accuracy of the algorithm female larger than burden?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "Are the values in the chart presented in a percentage scale?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "What is the accuracy of the algorithm burden?" }, { "from": "gpt", "value": "7." }, { "from": "human", "value": "What is the label of the first bar from the left?" }, { "from": "gpt", "value": "Dome." }, { "from": "human", "value": "Are the bars horizontal?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "How many bars are there?" }, { "from": "gpt", "value": "Five." } ]
dvqa(cauldron,llava_format)
cauldron/dvqa/images/dvqa_00099765.png
[ { "from": "human", "value": "How many algorithms have accuracy lower than 30 in at least one dataset?\nAnswer the question using a single word or phrase." }, { "from": "gpt", "value": "One." }, { "from": "human", "value": "Which algorithm has lowest accuracy for any dataset?" }, { "from": "gpt", "value": "Figure." }, { "from": "human", "value": "What is the lowest accuracy reported in the whole chart?" }, { "from": "gpt", "value": "20." }, { "from": "human", "value": "Which algorithm has the smallest accuracy summed across all the datasets?" }, { "from": "gpt", "value": "Sale." }, { "from": "human", "value": "Which algorithm has the largest accuracy summed across all the datasets?" }, { "from": "gpt", "value": "Neck." }, { "from": "human", "value": "Are the values in the chart presented in a percentage scale?" }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "What dataset does the lime color represent?" }, { "from": "gpt", "value": "Fall." }, { "from": "human", "value": "What is the accuracy of the algorithm figure in the dataset fall?" }, { "from": "gpt", "value": "20." }, { "from": "human", "value": "What is the label of the seventh group of bars from the left?" }, { "from": "gpt", "value": "Vertex." }, { "from": "human", "value": "What is the label of the first bar from the left in each group?" }, { "from": "gpt", "value": "Pace." }, { "from": "human", "value": "Is each bar a single solid color without patterns?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "How many groups of bars are there?" }, { "from": "gpt", "value": "Seven." } ]
dvqa(cauldron,llava_format)
cauldron/dvqa/images/dvqa_00099767.png
[ { "from": "human", "value": "How many groups of bars contain at least one bar with value smaller than 2?\nAnswer the question using a single word or phrase." }, { "from": "gpt", "value": "One." }, { "from": "human", "value": "Which group of bars contains the smallest valued individual bar in the whole chart?" }, { "from": "gpt", "value": "Hall." }, { "from": "human", "value": "What is the value of the smallest individual bar in the whole chart?" }, { "from": "gpt", "value": "1." }, { "from": "human", "value": "Which group has the smallest summed value?" }, { "from": "gpt", "value": "Hall." }, { "from": "human", "value": "Which group has the largest summed value?" }, { "from": "gpt", "value": "Blood." }, { "from": "human", "value": "What is the sum of all the values in the hall group?" }, { "from": "gpt", "value": "3." }, { "from": "human", "value": "Is the value of blood in garage smaller than the value of sugar in grass?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "Are the values in the chart presented in a percentage scale?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "What element does the steelblue color represent?" }, { "from": "gpt", "value": "Grass." }, { "from": "human", "value": "What is the value of grass in clay?" }, { "from": "gpt", "value": "7." }, { "from": "human", "value": "What is the label of the first group of bars from the left?" }, { "from": "gpt", "value": "Sugar." }, { "from": "human", "value": "What is the label of the second bar from the left in each group?" }, { "from": "gpt", "value": "Garage." }, { "from": "human", "value": "Are the bars horizontal?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "How many bars are there per group?" }, { "from": "gpt", "value": "Two." } ]
dvqa(cauldron,llava_format)
cauldron/dvqa/images/dvqa_00099768.png
[ { "from": "human", "value": "How many groups of bars contain at least one bar with value greater than 4?\nAnswer the question using a single word or phrase." }, { "from": "gpt", "value": "Four." }, { "from": "human", "value": "Which group has the smallest summed value?" }, { "from": "gpt", "value": "Letter." }, { "from": "human", "value": "Which group has the largest summed value?" }, { "from": "gpt", "value": "Credit." }, { "from": "human", "value": "Is the value of pond in horse larger than the value of office in sin?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "What element does the royalblue color represent?" }, { "from": "gpt", "value": "Sin." }, { "from": "human", "value": "What is the value of horse in office?" }, { "from": "gpt", "value": "3." }, { "from": "human", "value": "What is the label of the first group of bars from the left?" }, { "from": "gpt", "value": "Pond." }, { "from": "human", "value": "What is the label of the first bar from the left in each group?" }, { "from": "gpt", "value": "Horse." }, { "from": "human", "value": "Are the bars horizontal?" }, { "from": "gpt", "value": "No." } ]
dvqa(cauldron,llava_format)
cauldron/dvqa/images/dvqa_00099770.png
[ { "from": "human", "value": "How many items sold more than 8 units in at least one store?\nAnswer the question using a single word or phrase." }, { "from": "gpt", "value": "Zero." }, { "from": "human", "value": "Which item sold the least units in any shop?" }, { "from": "gpt", "value": "Gain." }, { "from": "human", "value": "How many units did the worst selling item sell in the whole chart?" }, { "from": "gpt", "value": "2." }, { "from": "human", "value": "Which item sold the least number of units summed across all the stores?" }, { "from": "gpt", "value": "Level." }, { "from": "human", "value": "Which item sold the most number of units summed across all the stores?" }, { "from": "gpt", "value": "Graph." }, { "from": "human", "value": "How many units of the item gain were sold across all the stores?" }, { "from": "gpt", "value": "10." }, { "from": "human", "value": "Did the item gain in the store melody sold smaller units than the item level in the store length?" }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "What store does the orchid color represent?" }, { "from": "gpt", "value": "Length." }, { "from": "human", "value": "How many units of the item gain were sold in the store melody?" }, { "from": "gpt", "value": "2." }, { "from": "human", "value": "What is the label of the first group of bars from the left?" }, { "from": "gpt", "value": "Graph." }, { "from": "human", "value": "What is the label of the first bar from the left in each group?" }, { "from": "gpt", "value": "Melody." } ]
dvqa(cauldron,llava_format)
cauldron/dvqa/images/dvqa_00099771.png
[ { "from": "human", "value": "How many algorithms have accuracy higher than 1 in at least one dataset?\nAnswer the question using a single word or phrase." }, { "from": "gpt", "value": "Four." }, { "from": "human", "value": "Which algorithm has highest accuracy for any dataset?" }, { "from": "gpt", "value": "Study." }, { "from": "human", "value": "What is the highest accuracy reported in the whole chart?" }, { "from": "gpt", "value": "9." }, { "from": "human", "value": "Which algorithm has the smallest accuracy summed across all the datasets?" }, { "from": "gpt", "value": "Editor." }, { "from": "human", "value": "Which algorithm has the largest accuracy summed across all the datasets?" }, { "from": "gpt", "value": "Study." }, { "from": "human", "value": "What is the sum of accuracies of the algorithm hung for all the datasets?" }, { "from": "gpt", "value": "12." }, { "from": "human", "value": "Is the accuracy of the algorithm study in the dataset lumber smaller than the accuracy of the algorithm editor in the dataset inside?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "What dataset does the darkorange color represent?" }, { "from": "gpt", "value": "Inside." }, { "from": "human", "value": "What is the accuracy of the algorithm study in the dataset lumber?" }, { "from": "gpt", "value": "9." }, { "from": "human", "value": "What is the label of the third group of bars from the left?" }, { "from": "gpt", "value": "Hung." }, { "from": "human", "value": "What is the label of the first bar from the left in each group?" }, { "from": "gpt", "value": "Lumber." } ]
dvqa(cauldron,llava_format)
cauldron/dvqa/images/dvqa_00099777.png
[ { "from": "human", "value": "How many objects are preferred by more than 40 percent of people in at least one category?\nAnswer the question using a single word or phrase." }, { "from": "gpt", "value": "One." }, { "from": "human", "value": "Which object is the most preferred in any category?" }, { "from": "gpt", "value": "Moment." }, { "from": "human", "value": "Which object is the least preferred in any category?" }, { "from": "gpt", "value": "Moment." }, { "from": "human", "value": "What percentage of people like the most preferred object in the whole chart?" }, { "from": "gpt", "value": "50." }, { "from": "human", "value": "What percentage of people like the least preferred object in the whole chart?" }, { "from": "gpt", "value": "10." }, { "from": "human", "value": "Is the value of file in edge smaller than the value of moment in vacuum?" }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "Are the values in the chart presented in a percentage scale?" }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "What category does the steelblue color represent?" }, { "from": "gpt", "value": "Holder." }, { "from": "human", "value": "What percentage of people prefer the object file in the category edge?" }, { "from": "gpt", "value": "40." }, { "from": "human", "value": "What is the label of the first group of bars from the bottom?" }, { "from": "gpt", "value": "File." }, { "from": "human", "value": "What is the label of the first bar from the bottom in each group?" }, { "from": "gpt", "value": "Edge." }, { "from": "human", "value": "Are the bars horizontal?" }, { "from": "gpt", "value": "Yes." } ]
dvqa(cauldron,llava_format)
cauldron/dvqa/images/dvqa_00099781.png
[ { "from": "human", "value": "How many groups of bars contain at least one bar with value smaller than 3?\nAnswer the question using a single word or phrase." }, { "from": "gpt", "value": "One." }, { "from": "human", "value": "Which group of bars contains the smallest valued individual bar in the whole chart?" }, { "from": "gpt", "value": "Jet." }, { "from": "human", "value": "What is the value of the smallest individual bar in the whole chart?" }, { "from": "gpt", "value": "2." }, { "from": "human", "value": "Which group has the smallest summed value?" }, { "from": "gpt", "value": "Jet." }, { "from": "human", "value": "Which group has the largest summed value?" }, { "from": "gpt", "value": "Center." }, { "from": "human", "value": "What is the sum of all the values in the jet group?" }, { "from": "gpt", "value": "12." }, { "from": "human", "value": "Is the value of handle in trail larger than the value of center in crash?" }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "Are the values in the chart presented in a percentage scale?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "What element does the darkorange color represent?" }, { "from": "gpt", "value": "Trail." }, { "from": "human", "value": "What is the value of crash in suit?" }, { "from": "gpt", "value": "3." }, { "from": "human", "value": "What is the label of the second group of bars from the left?" }, { "from": "gpt", "value": "Slave." }, { "from": "human", "value": "What is the label of the third bar from the left in each group?" }, { "from": "gpt", "value": "Angle." }, { "from": "human", "value": "Is each bar a single solid color without patterns?" }, { "from": "gpt", "value": "Yes." } ]
dvqa(cauldron,llava_format)
cauldron/dvqa/images/dvqa_00099785.png
[ { "from": "human", "value": "Which item sold the most units?\nAnswer the question using a single word or phrase." }, { "from": "gpt", "value": "Stay." }, { "from": "human", "value": "Which item sold the least units?" }, { "from": "gpt", "value": "Nation." }, { "from": "human", "value": "How many units of the the most sold item were sold?" }, { "from": "gpt", "value": "8." }, { "from": "human", "value": "How many units of the the least sold item were sold?" }, { "from": "gpt", "value": "3." }, { "from": "human", "value": "How many more of the most sold item were sold compared to the least sold item?" }, { "from": "gpt", "value": "5." }, { "from": "human", "value": "How many items sold less than 7 units?" }, { "from": "gpt", "value": "Two." }, { "from": "human", "value": "How many units of items honor and nation were sold?" }, { "from": "gpt", "value": "10." }, { "from": "human", "value": "Did the item anger sold more units than point?" }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "Are the values in the chart presented in a percentage scale?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "How many units of the item nation were sold?" }, { "from": "gpt", "value": "3." }, { "from": "human", "value": "What is the label of the first bar from the bottom?" }, { "from": "gpt", "value": "Nation." }, { "from": "human", "value": "Are the bars horizontal?" }, { "from": "gpt", "value": "Yes." } ]
dvqa(cauldron,llava_format)
cauldron/dvqa/images/dvqa_00099789.png
[ { "from": "human", "value": "Which algorithm has the highest accuracy?\nAnswer the question using a single word or phrase." }, { "from": "gpt", "value": "Owner." }, { "from": "human", "value": "Which algorithm has the lowest accuracy?" }, { "from": "gpt", "value": "Market." }, { "from": "human", "value": "What is the accuracy of the algorithm with highest accuracy?" }, { "from": "gpt", "value": "8." }, { "from": "human", "value": "What is the accuracy of the algorithm with lowest accuracy?" }, { "from": "gpt", "value": "1." }, { "from": "human", "value": "How much more accurate is the most accurate algorithm compared the least accurate algorithm?" }, { "from": "gpt", "value": "7." }, { "from": "human", "value": "How many algorithms have accuracies higher than 3?" }, { "from": "gpt", "value": "Two." }, { "from": "human", "value": "What is the sum of the accuracies of the algorithms market and owner?" }, { "from": "gpt", "value": "9." }, { "from": "human", "value": "Is the accuracy of the algorithm owner smaller than market?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "Are the values in the chart presented in a percentage scale?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "What is the accuracy of the algorithm behalf?" }, { "from": "gpt", "value": "2." }, { "from": "human", "value": "What is the label of the fifth bar from the left?" }, { "from": "gpt", "value": "Actor." }, { "from": "human", "value": "Is each bar a single solid color without patterns?" }, { "from": "gpt", "value": "No." } ]
dvqa(cauldron,llava_format)
cauldron/dvqa/images/dvqa_00099791.png
[ { "from": "human", "value": "How many groups of bars contain at least one bar with value smaller than 4?\nAnswer the question using a single word or phrase." }, { "from": "gpt", "value": "Four." }, { "from": "human", "value": "Which group has the largest summed value?" }, { "from": "gpt", "value": "Case." }, { "from": "human", "value": "Is the value of stairs in image smaller than the value of case in poem?" }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "Are the values in the chart presented in a percentage scale?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "What element does the powderblue color represent?" }, { "from": "gpt", "value": "Autumn." }, { "from": "human", "value": "What is the value of poem in foam?" }, { "from": "gpt", "value": "1." }, { "from": "human", "value": "What is the label of the third group of bars from the left?" }, { "from": "gpt", "value": "Lobby." }, { "from": "human", "value": "What is the label of the third bar from the left in each group?" }, { "from": "gpt", "value": "Image." }, { "from": "human", "value": "Are the bars horizontal?" }, { "from": "gpt", "value": "No." } ]
dvqa(cauldron,llava_format)
cauldron/dvqa/images/dvqa_00099795.png
[ { "from": "human", "value": "How many objects are preferred by less than 9 people in at least one category?\nAnswer the question using a single word or phrase." }, { "from": "gpt", "value": "Seven." }, { "from": "human", "value": "Which object is the most preferred in any category?" }, { "from": "gpt", "value": "Hold." }, { "from": "human", "value": "How many people like the most preferred object in the whole chart?" }, { "from": "gpt", "value": "9." }, { "from": "human", "value": "Which object is preferred by the least number of people summed across all the categories?" }, { "from": "gpt", "value": "Weight." }, { "from": "human", "value": "Which object is preferred by the most number of people summed across all the categories?" }, { "from": "gpt", "value": "Taxi." }, { "from": "human", "value": "How many total people preferred the object rhythm across all the categories?" }, { "from": "gpt", "value": "10." }, { "from": "human", "value": "Is the object taxi in the category wisdom preferred by more people than the object debate in the category rank?" }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "What category does the steelblue color represent?" }, { "from": "gpt", "value": "Wisdom." }, { "from": "human", "value": "How many people prefer the object taxi in the category honey?" }, { "from": "gpt", "value": "7." }, { "from": "human", "value": "What is the label of the fifth group of bars from the left?" }, { "from": "gpt", "value": "Taxi." }, { "from": "human", "value": "What is the label of the first bar from the left in each group?" }, { "from": "gpt", "value": "Wisdom." } ]
dvqa(cauldron,llava_format)
cauldron/dvqa/images/dvqa_00099800.png
[ { "from": "human", "value": "Which algorithm has the highest accuracy?\nAnswer the question using a single word or phrase." }, { "from": "gpt", "value": "Beam." }, { "from": "human", "value": "Which algorithm has the lowest accuracy?" }, { "from": "gpt", "value": "River." }, { "from": "human", "value": "What is the accuracy of the algorithm with highest accuracy?" }, { "from": "gpt", "value": "9." }, { "from": "human", "value": "What is the accuracy of the algorithm with lowest accuracy?" }, { "from": "gpt", "value": "2." }, { "from": "human", "value": "How much more accurate is the most accurate algorithm compared the least accurate algorithm?" }, { "from": "gpt", "value": "7." }, { "from": "human", "value": "How many algorithms have accuracies higher than 5?" }, { "from": "gpt", "value": "One." }, { "from": "human", "value": "What is the sum of the accuracies of the algorithms beam and metal?" }, { "from": "gpt", "value": "14." }, { "from": "human", "value": "Is the accuracy of the algorithm river larger than metal?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "What is the accuracy of the algorithm myth?" }, { "from": "gpt", "value": "5." }, { "from": "human", "value": "What is the label of the third bar from the left?" }, { "from": "gpt", "value": "Myth." }, { "from": "human", "value": "Are the bars horizontal?" }, { "from": "gpt", "value": "No." } ]
dvqa(cauldron,llava_format)
cauldron/dvqa/images/dvqa_00099802.png
[ { "from": "human", "value": "Which object is the most preferred?\nAnswer the question using a single word or phrase." }, { "from": "gpt", "value": "Length." }, { "from": "human", "value": "Which object is the least preferred?" }, { "from": "gpt", "value": "Money." }, { "from": "human", "value": "How many people prefer the most preferred object?" }, { "from": "gpt", "value": "6." }, { "from": "human", "value": "How many people prefer the least preferred object?" }, { "from": "gpt", "value": "1." }, { "from": "human", "value": "What is the difference between most and least preferred object?" }, { "from": "gpt", "value": "5." }, { "from": "human", "value": "How many objects are liked by less than 1 people?" }, { "from": "gpt", "value": "Zero." }, { "from": "human", "value": "How many people prefer the objects length or engine?" }, { "from": "gpt", "value": "9." }, { "from": "human", "value": "Is the object drug preferred by more people than length?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "How many people prefer the object length?" }, { "from": "gpt", "value": "6." }, { "from": "human", "value": "What is the label of the fourth bar from the left?" }, { "from": "gpt", "value": "Drug." }, { "from": "human", "value": "Is each bar a single solid color without patterns?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "How many bars are there?" }, { "from": "gpt", "value": "Four." } ]
dvqa(cauldron,llava_format)
cauldron/dvqa/images/dvqa_00099813.png
[ { "from": "human", "value": "Which object is the most preferred?\nAnswer the question using a single word or phrase." }, { "from": "gpt", "value": "Mind." }, { "from": "human", "value": "Which object is the least preferred?" }, { "from": "gpt", "value": "Stem." }, { "from": "human", "value": "How many people prefer the most preferred object?" }, { "from": "gpt", "value": "7." }, { "from": "human", "value": "How many people prefer the least preferred object?" }, { "from": "gpt", "value": "4." }, { "from": "human", "value": "What is the difference between most and least preferred object?" }, { "from": "gpt", "value": "3." }, { "from": "human", "value": "How many objects are liked by less than 7 people?" }, { "from": "gpt", "value": "Two." }, { "from": "human", "value": "How many people prefer the objects mind or stem?" }, { "from": "gpt", "value": "11." }, { "from": "human", "value": "Is the object stem preferred by less people than mind?" }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "How many people prefer the object bass?" }, { "from": "gpt", "value": "6." }, { "from": "human", "value": "What is the label of the second bar from the left?" }, { "from": "gpt", "value": "Stem." } ]
dvqa(cauldron,llava_format)
cauldron/dvqa/images/dvqa_00099814.png
[ { "from": "human", "value": "Which object is the most preferred?\nAnswer the question using a single word or phrase." }, { "from": "gpt", "value": "Look." }, { "from": "human", "value": "Which object is the least preferred?" }, { "from": "gpt", "value": "Bond." }, { "from": "human", "value": "How many people prefer the most preferred object?" }, { "from": "gpt", "value": "7." }, { "from": "human", "value": "How many people prefer the least preferred object?" }, { "from": "gpt", "value": "1." }, { "from": "human", "value": "What is the difference between most and least preferred object?" }, { "from": "gpt", "value": "6." }, { "from": "human", "value": "How many objects are liked by more than 7 people?" }, { "from": "gpt", "value": "Zero." }, { "from": "human", "value": "How many people prefer the objects column or look?" }, { "from": "gpt", "value": "9." }, { "from": "human", "value": "Is the object dawn preferred by less people than bond?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "Are the values in the chart presented in a percentage scale?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "How many people prefer the object wonder?" }, { "from": "gpt", "value": "5." }, { "from": "human", "value": "What is the label of the third bar from the left?" }, { "from": "gpt", "value": "Rice." }, { "from": "human", "value": "Does the chart contain stacked bars?" }, { "from": "gpt", "value": "No." } ]
dvqa(cauldron,llava_format)
cauldron/dvqa/images/dvqa_00099819.png
[ { "from": "human", "value": "How many groups of bars contain at least one bar with value greater than 9?\nAnswer the question using a single word or phrase." }, { "from": "gpt", "value": "Zero." }, { "from": "human", "value": "Which group has the smallest summed value?" }, { "from": "gpt", "value": "Rage." }, { "from": "human", "value": "What is the sum of all the values in the belt group?" }, { "from": "gpt", "value": "13." }, { "from": "human", "value": "What element does the darkorange color represent?" }, { "from": "gpt", "value": "Wheel." }, { "from": "human", "value": "What is the value of meat in break?" }, { "from": "gpt", "value": "2." }, { "from": "human", "value": "What is the label of the third group of bars from the left?" }, { "from": "gpt", "value": "Belt." }, { "from": "human", "value": "What is the label of the first bar from the left in each group?" }, { "from": "gpt", "value": "Meat." }, { "from": "human", "value": "Are the bars horizontal?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "Is each bar a single solid color without patterns?" }, { "from": "gpt", "value": "No." } ]
dvqa(cauldron,llava_format)
cauldron/dvqa/images/dvqa_00099822.png
[ { "from": "human", "value": "How many algorithms have accuracy lower than 70 in at least one dataset?\nAnswer the question using a single word or phrase." }, { "from": "gpt", "value": "Two." }, { "from": "human", "value": "Which algorithm has highest accuracy for any dataset?" }, { "from": "gpt", "value": "Movie." }, { "from": "human", "value": "Which algorithm has lowest accuracy for any dataset?" }, { "from": "gpt", "value": "Movie." }, { "from": "human", "value": "What is the highest accuracy reported in the whole chart?" }, { "from": "gpt", "value": "70." }, { "from": "human", "value": "What is the lowest accuracy reported in the whole chart?" }, { "from": "gpt", "value": "30." }, { "from": "human", "value": "Is the accuracy of the algorithm pilot in the dataset stairs larger than the accuracy of the algorithm movie in the dataset peace?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "Are the values in the chart presented in a percentage scale?" }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "What dataset does the palegoldenrod color represent?" }, { "from": "gpt", "value": "Peace." }, { "from": "human", "value": "What is the accuracy of the algorithm pilot in the dataset stairs?" }, { "from": "gpt", "value": "40." }, { "from": "human", "value": "What is the label of the first group of bars from the left?" }, { "from": "gpt", "value": "Movie." }, { "from": "human", "value": "What is the label of the first bar from the left in each group?" }, { "from": "gpt", "value": "Stairs." }, { "from": "human", "value": "Are the bars horizontal?" }, { "from": "gpt", "value": "No." } ]
dvqa(cauldron,llava_format)
cauldron/dvqa/images/dvqa_00099827.png
[ { "from": "human", "value": "Which object is the most preferred?\nAnswer the question using a single word or phrase." }, { "from": "gpt", "value": "Flight." }, { "from": "human", "value": "Which object is the least preferred?" }, { "from": "gpt", "value": "Agent." }, { "from": "human", "value": "What percentage of people prefer the most preferred object?" }, { "from": "gpt", "value": "90." }, { "from": "human", "value": "What percentage of people prefer the least preferred object?" }, { "from": "gpt", "value": "20." }, { "from": "human", "value": "What is the difference between most and least preferred object?" }, { "from": "gpt", "value": "70." }, { "from": "human", "value": "How many objects are liked by less than 20 percent of people?" }, { "from": "gpt", "value": "Zero." }, { "from": "human", "value": "Is the object flight preferred by less people than agent?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "Are the values in the chart presented in a percentage scale?" }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "What percentage of people prefer the object agent?" }, { "from": "gpt", "value": "20." }, { "from": "human", "value": "What is the label of the third bar from the left?" }, { "from": "gpt", "value": "Ocean." } ]
dvqa(cauldron,llava_format)
cauldron/dvqa/images/dvqa_00099828.png
[ { "from": "human", "value": "Which item sold the most units?\nAnswer the question using a single word or phrase." }, { "from": "gpt", "value": "Ticket." }, { "from": "human", "value": "How many units of the the most sold item were sold?" }, { "from": "gpt", "value": "9." }, { "from": "human", "value": "How many items sold less than 7 units?" }, { "from": "gpt", "value": "Three." }, { "from": "human", "value": "How many units of items fuel and class were sold?" }, { "from": "gpt", "value": "15." }, { "from": "human", "value": "Did the item era sold more units than roof?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "How many units of the item fuel were sold?" }, { "from": "gpt", "value": "7." }, { "from": "human", "value": "What is the label of the fifth bar from the bottom?" }, { "from": "gpt", "value": "Roof." }, { "from": "human", "value": "Are the bars horizontal?" }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "Does the chart contain stacked bars?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "Is each bar a single solid color without patterns?" }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "How many bars are there?" }, { "from": "gpt", "value": "Seven." } ]
dvqa(cauldron,llava_format)
cauldron/dvqa/images/dvqa_00099830.png
[ { "from": "human", "value": "How many groups of bars contain at least one bar with value smaller than 4?\nAnswer the question using a single word or phrase." }, { "from": "gpt", "value": "Five." }, { "from": "human", "value": "Which group of bars contains the largest valued individual bar in the whole chart?" }, { "from": "gpt", "value": "Dream." }, { "from": "human", "value": "What is the value of the largest individual bar in the whole chart?" }, { "from": "gpt", "value": "9." }, { "from": "human", "value": "Which group has the smallest summed value?" }, { "from": "gpt", "value": "Humor." }, { "from": "human", "value": "Which group has the largest summed value?" }, { "from": "gpt", "value": "Dream." }, { "from": "human", "value": "Is the value of speed in fish smaller than the value of cause in edge?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "What element does the forestgreen color represent?" }, { "from": "gpt", "value": "Edge." }, { "from": "human", "value": "What is the value of effort in speed?" }, { "from": "gpt", "value": "6." }, { "from": "human", "value": "What is the label of the fifth group of bars from the bottom?" }, { "from": "gpt", "value": "Dream." }, { "from": "human", "value": "What is the label of the second bar from the bottom in each group?" }, { "from": "gpt", "value": "Fish." }, { "from": "human", "value": "Are the bars horizontal?" }, { "from": "gpt", "value": "Yes." } ]
dvqa(cauldron,llava_format)
cauldron/dvqa/images/dvqa_00099838.png
[ { "from": "human", "value": "How many groups of bars contain at least one bar with value greater than 8?\nAnswer the question using a single word or phrase." }, { "from": "gpt", "value": "Two." }, { "from": "human", "value": "Which group has the smallest summed value?" }, { "from": "gpt", "value": "Boss." }, { "from": "human", "value": "Which group has the largest summed value?" }, { "from": "gpt", "value": "Brush." }, { "from": "human", "value": "What is the sum of all the values in the brush group?" }, { "from": "gpt", "value": "27." }, { "from": "human", "value": "Is the value of boss in form smaller than the value of brush in actor?" }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "What element does the sienna color represent?" }, { "from": "gpt", "value": "Actor." }, { "from": "human", "value": "What is the value of supply in boss?" }, { "from": "gpt", "value": "4." }, { "from": "human", "value": "What is the label of the second group of bars from the left?" }, { "from": "gpt", "value": "Hold." }, { "from": "human", "value": "What is the label of the first bar from the left in each group?" }, { "from": "gpt", "value": "Supply." }, { "from": "human", "value": "Is each bar a single solid color without patterns?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "How many bars are there per group?" }, { "from": "gpt", "value": "Four." } ]
dvqa(cauldron,llava_format)
cauldron/dvqa/images/dvqa_00099850.png
[ { "from": "human", "value": "How many algorithms have accuracy higher than 5 in at least one dataset?\nAnswer the question using a single word or phrase." }, { "from": "gpt", "value": "Five." }, { "from": "human", "value": "Which algorithm has the smallest accuracy summed across all the datasets?" }, { "from": "gpt", "value": "Unit." }, { "from": "human", "value": "What is the sum of accuracies of the algorithm cow for all the datasets?" }, { "from": "gpt", "value": "7." }, { "from": "human", "value": "Is the accuracy of the algorithm unit in the dataset humor smaller than the accuracy of the algorithm pocket in the dataset way?" }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "What dataset does the darkorange color represent?" }, { "from": "gpt", "value": "Humor." }, { "from": "human", "value": "What is the accuracy of the algorithm sand in the dataset humor?" }, { "from": "gpt", "value": "5." }, { "from": "human", "value": "What is the label of the fourth group of bars from the bottom?" }, { "from": "gpt", "value": "Spot." }, { "from": "human", "value": "What is the label of the first bar from the bottom in each group?" }, { "from": "gpt", "value": "Way." }, { "from": "human", "value": "Are the bars horizontal?" }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "How many groups of bars are there?" }, { "from": "gpt", "value": "Nine." } ]
dvqa(cauldron,llava_format)
cauldron/dvqa/images/dvqa_00099851.png
[ { "from": "human", "value": "Which algorithm has the highest accuracy?\nAnswer the question using a single word or phrase." }, { "from": "gpt", "value": "Flux." }, { "from": "human", "value": "Which algorithm has the lowest accuracy?" }, { "from": "gpt", "value": "Tone." }, { "from": "human", "value": "What is the accuracy of the algorithm with highest accuracy?" }, { "from": "gpt", "value": "60." }, { "from": "human", "value": "What is the accuracy of the algorithm with lowest accuracy?" }, { "from": "gpt", "value": "50." }, { "from": "human", "value": "How much more accurate is the most accurate algorithm compared the least accurate algorithm?" }, { "from": "gpt", "value": "10." }, { "from": "human", "value": "How many algorithms have accuracies lower than 50?" }, { "from": "gpt", "value": "Zero." }, { "from": "human", "value": "Is the accuracy of the algorithm flux larger than tone?" }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "Are the values in the chart presented in a percentage scale?" }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "What is the accuracy of the algorithm tone?" }, { "from": "gpt", "value": "50." }, { "from": "human", "value": "What is the label of the second bar from the left?" }, { "from": "gpt", "value": "Tone." }, { "from": "human", "value": "Are the bars horizontal?" }, { "from": "gpt", "value": "No." } ]
dvqa(cauldron,llava_format)
cauldron/dvqa/images/dvqa_00099852.png
[ { "from": "human", "value": "Which object is the most preferred?\nAnswer the question using a single word or phrase." }, { "from": "gpt", "value": "Foam." }, { "from": "human", "value": "Which object is the least preferred?" }, { "from": "gpt", "value": "Police." }, { "from": "human", "value": "How many people prefer the most preferred object?" }, { "from": "gpt", "value": "8." }, { "from": "human", "value": "How many people prefer the least preferred object?" }, { "from": "gpt", "value": "1." }, { "from": "human", "value": "What is the difference between most and least preferred object?" }, { "from": "gpt", "value": "7." }, { "from": "human", "value": "How many objects are liked by less than 3 people?" }, { "from": "gpt", "value": "One." }, { "from": "human", "value": "How many people prefer the objects graph or foam?" }, { "from": "gpt", "value": "11." }, { "from": "human", "value": "Is the object graph preferred by less people than police?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "How many people prefer the object police?" }, { "from": "gpt", "value": "1." }, { "from": "human", "value": "What is the label of the second bar from the bottom?" }, { "from": "gpt", "value": "Graph." }, { "from": "human", "value": "Are the bars horizontal?" }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "Is each bar a single solid color without patterns?" }, { "from": "gpt", "value": "Yes." } ]
dvqa(cauldron,llava_format)
cauldron/dvqa/images/dvqa_00099853.png
[ { "from": "human", "value": "Which object is the most preferred?\nAnswer the question using a single word or phrase." }, { "from": "gpt", "value": "Fly." }, { "from": "human", "value": "Which object is the least preferred?" }, { "from": "gpt", "value": "Visit." }, { "from": "human", "value": "What percentage of people prefer the most preferred object?" }, { "from": "gpt", "value": "80." }, { "from": "human", "value": "What percentage of people prefer the least preferred object?" }, { "from": "gpt", "value": "10." }, { "from": "human", "value": "What is the difference between most and least preferred object?" }, { "from": "gpt", "value": "70." }, { "from": "human", "value": "How many objects are liked by less than 80 percent of people?" }, { "from": "gpt", "value": "Six." }, { "from": "human", "value": "Is the object loan preferred by more people than fly?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "Are the values in the chart presented in a percentage scale?" }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "What percentage of people prefer the object loan?" }, { "from": "gpt", "value": "40." }, { "from": "human", "value": "What is the label of the second bar from the left?" }, { "from": "gpt", "value": "Loan." }, { "from": "human", "value": "Is each bar a single solid color without patterns?" }, { "from": "gpt", "value": "Yes." } ]
dvqa(cauldron,llava_format)
cauldron/dvqa/images/dvqa_00099856.png
[ { "from": "human", "value": "How many algorithms have accuracy lower than 10 in at least one dataset?\nAnswer the question using a single word or phrase." }, { "from": "gpt", "value": "Zero." }, { "from": "human", "value": "Which algorithm has the smallest accuracy summed across all the datasets?" }, { "from": "gpt", "value": "Bay." }, { "from": "human", "value": "Which algorithm has the largest accuracy summed across all the datasets?" }, { "from": "gpt", "value": "Sake." }, { "from": "human", "value": "Is the accuracy of the algorithm trust in the dataset piece larger than the accuracy of the algorithm sake in the dataset load?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "Are the values in the chart presented in a percentage scale?" }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "What dataset does the mediumseagreen color represent?" }, { "from": "gpt", "value": "Number." }, { "from": "human", "value": "What is the accuracy of the algorithm sake in the dataset number?" }, { "from": "gpt", "value": "90." }, { "from": "human", "value": "What is the label of the first group of bars from the left?" }, { "from": "gpt", "value": "Powder." }, { "from": "human", "value": "What is the label of the first bar from the left in each group?" }, { "from": "gpt", "value": "Piece." }, { "from": "human", "value": "How many bars are there per group?" }, { "from": "gpt", "value": "Four." } ]
dvqa(cauldron,llava_format)
cauldron/dvqa/images/dvqa_00099859.png
[ { "from": "human", "value": "How many stacks of bars contain at least one element with value smaller than 8?\nAnswer the question using a single word or phrase." }, { "from": "gpt", "value": "Four." }, { "from": "human", "value": "Which stack of bars contains the smallest valued individual element in the whole chart?" }, { "from": "gpt", "value": "Notice." }, { "from": "human", "value": "What is the value of the smallest individual element in the whole chart?" }, { "from": "gpt", "value": "1." }, { "from": "human", "value": "Which stack of bars has the largest summed value?" }, { "from": "gpt", "value": "Pile." }, { "from": "human", "value": "What is the sum of all the values in the pile group?" }, { "from": "gpt", "value": "33." }, { "from": "human", "value": "What element does the forestgreen color represent?" }, { "from": "gpt", "value": "Band." }, { "from": "human", "value": "What is the value of beard in middle?" }, { "from": "gpt", "value": "3." }, { "from": "human", "value": "What is the label of the second stack of bars from the left?" }, { "from": "gpt", "value": "Shadow." }, { "from": "human", "value": "What is the label of the fourth element from the bottom in each stack of bars?" }, { "from": "gpt", "value": "Finger." }, { "from": "human", "value": "Are the bars horizontal?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "Does the chart contain stacked bars?" }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "How many elements are there in each stack of bars?" }, { "from": "gpt", "value": "Four." } ]
dvqa(cauldron,llava_format)
cauldron/dvqa/images/dvqa_00099865.png
[ { "from": "human", "value": "How many objects are preferred by less than 8 people in at least one category?\nAnswer the question using a single word or phrase." }, { "from": "gpt", "value": "Eight." }, { "from": "human", "value": "Which object is the most preferred in any category?" }, { "from": "gpt", "value": "Output." }, { "from": "human", "value": "How many people like the most preferred object in the whole chart?" }, { "from": "gpt", "value": "9." }, { "from": "human", "value": "Which object is preferred by the most number of people summed across all the categories?" }, { "from": "gpt", "value": "Output." }, { "from": "human", "value": "How many total people preferred the object mirror across all the categories?" }, { "from": "gpt", "value": "16." }, { "from": "human", "value": "Is the object board in the category member preferred by less people than the object mirror in the category end?" }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "What category does the green color represent?" }, { "from": "gpt", "value": "Member." }, { "from": "human", "value": "How many people prefer the object theme in the category fiber?" }, { "from": "gpt", "value": "7." }, { "from": "human", "value": "What is the label of the seventh stack of bars from the bottom?" }, { "from": "gpt", "value": "Laugh." }, { "from": "human", "value": "What is the label of the first element from the left in each stack of bars?" }, { "from": "gpt", "value": "Fiber." }, { "from": "human", "value": "Are the bars horizontal?" }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "Does the chart contain stacked bars?" }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "How many stacks of bars are there?" }, { "from": "gpt", "value": "Eight." } ]
dvqa(cauldron,llava_format)
cauldron/dvqa/images/dvqa_00099867.png
[ { "from": "human", "value": "How many objects are preferred by less than 7 people in at least one category?\nAnswer the question using a single word or phrase." }, { "from": "gpt", "value": "Two." }, { "from": "human", "value": "Which object is the most preferred in any category?" }, { "from": "gpt", "value": "Race." }, { "from": "human", "value": "Which object is the least preferred in any category?" }, { "from": "gpt", "value": "Mode." }, { "from": "human", "value": "How many people like the most preferred object in the whole chart?" }, { "from": "gpt", "value": "9." }, { "from": "human", "value": "How many people like the least preferred object in the whole chart?" }, { "from": "gpt", "value": "1." }, { "from": "human", "value": "Which object is preferred by the least number of people summed across all the categories?" }, { "from": "gpt", "value": "Mode." }, { "from": "human", "value": "Which object is preferred by the most number of people summed across all the categories?" }, { "from": "gpt", "value": "Race." }, { "from": "human", "value": "How many total people preferred the object mode across all the categories?" }, { "from": "gpt", "value": "9." }, { "from": "human", "value": "Is the object race in the category rise preferred by less people than the object mode in the category shame?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "Are the values in the chart presented in a percentage scale?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "What category does the crimson color represent?" }, { "from": "gpt", "value": "Fact." }, { "from": "human", "value": "How many people prefer the object mode in the category fact?" }, { "from": "gpt", "value": "4." }, { "from": "human", "value": "What is the label of the second group of bars from the left?" }, { "from": "gpt", "value": "Race." }, { "from": "human", "value": "What is the label of the first bar from the left in each group?" }, { "from": "gpt", "value": "Rise." }, { "from": "human", "value": "Are the bars horizontal?" }, { "from": "gpt", "value": "No." } ]
dvqa(cauldron,llava_format)
cauldron/dvqa/images/dvqa_00099868.png
[ { "from": "human", "value": "Which object is the most preferred?\nAnswer the question using a single word or phrase." }, { "from": "gpt", "value": "Page." }, { "from": "human", "value": "Which object is the least preferred?" }, { "from": "gpt", "value": "Jungle." }, { "from": "human", "value": "How many people prefer the most preferred object?" }, { "from": "gpt", "value": "7." }, { "from": "human", "value": "How many people prefer the least preferred object?" }, { "from": "gpt", "value": "2." }, { "from": "human", "value": "What is the difference between most and least preferred object?" }, { "from": "gpt", "value": "5." }, { "from": "human", "value": "How many objects are liked by more than 2 people?" }, { "from": "gpt", "value": "Two." }, { "from": "human", "value": "How many people prefer the objects help or page?" }, { "from": "gpt", "value": "13." }, { "from": "human", "value": "Is the object help preferred by less people than jungle?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "How many people prefer the object page?" }, { "from": "gpt", "value": "7." }, { "from": "human", "value": "What is the label of the second bar from the bottom?" }, { "from": "gpt", "value": "Page." }, { "from": "human", "value": "Are the bars horizontal?" }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "How many bars are there?" }, { "from": "gpt", "value": "Three." } ]
dvqa(cauldron,llava_format)
cauldron/dvqa/images/dvqa_00099872.png
[ { "from": "human", "value": "How many objects are preferred by less than 6 people in at least one category?\nAnswer the question using a single word or phrase." }, { "from": "gpt", "value": "One." }, { "from": "human", "value": "Which object is the most preferred in any category?" }, { "from": "gpt", "value": "While." }, { "from": "human", "value": "Which object is the least preferred in any category?" }, { "from": "gpt", "value": "Twenty." }, { "from": "human", "value": "How many people like the most preferred object in the whole chart?" }, { "from": "gpt", "value": "8." }, { "from": "human", "value": "How many people like the least preferred object in the whole chart?" }, { "from": "gpt", "value": "1." }, { "from": "human", "value": "Which object is preferred by the least number of people summed across all the categories?" }, { "from": "gpt", "value": "Twenty." }, { "from": "human", "value": "Which object is preferred by the most number of people summed across all the categories?" }, { "from": "gpt", "value": "While." }, { "from": "human", "value": "How many total people preferred the object twenty across all the categories?" }, { "from": "gpt", "value": "4." }, { "from": "human", "value": "Is the object twenty in the category matter preferred by more people than the object while in the category coast?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "What category does the blue color represent?" }, { "from": "gpt", "value": "Coast." }, { "from": "human", "value": "How many people prefer the object while in the category coast?" }, { "from": "gpt", "value": "6." }, { "from": "human", "value": "What is the label of the first group of bars from the left?" }, { "from": "gpt", "value": "Twenty." }, { "from": "human", "value": "What is the label of the second bar from the left in each group?" }, { "from": "gpt", "value": "Matter." }, { "from": "human", "value": "Are the bars horizontal?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "Is each bar a single solid color without patterns?" }, { "from": "gpt", "value": "Yes." } ]
dvqa(cauldron,llava_format)
cauldron/dvqa/images/dvqa_00099877.png
[ { "from": "human", "value": "How many groups of bars contain at least one bar with value smaller than 5?\nAnswer the question using a single word or phrase." }, { "from": "gpt", "value": "Three." }, { "from": "human", "value": "Which group of bars contains the smallest valued individual bar in the whole chart?" }, { "from": "gpt", "value": "Fellow." }, { "from": "human", "value": "What is the value of the smallest individual bar in the whole chart?" }, { "from": "gpt", "value": "-6." }, { "from": "human", "value": "Which group has the smallest summed value?" }, { "from": "gpt", "value": "Laugh." }, { "from": "human", "value": "Is the value of fellow in way larger than the value of laugh in excess?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "What element does the green color represent?" }, { "from": "gpt", "value": "Way." }, { "from": "human", "value": "What is the value of way in woman?" }, { "from": "gpt", "value": "-2." }, { "from": "human", "value": "What is the label of the first group of bars from the left?" }, { "from": "gpt", "value": "Woman." }, { "from": "human", "value": "What is the label of the third bar from the left in each group?" }, { "from": "gpt", "value": "Excess." }, { "from": "human", "value": "Does the chart contain any negative values?" }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "Is each bar a single solid color without patterns?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "How many bars are there per group?" }, { "from": "gpt", "value": "Three." } ]
dvqa(cauldron,llava_format)
cauldron/dvqa/images/dvqa_00099879.png
[ { "from": "human", "value": "How many groups of bars contain at least one bar with value greater than 7?\nAnswer the question using a single word or phrase." }, { "from": "gpt", "value": "One." }, { "from": "human", "value": "Which group of bars contains the largest valued individual bar in the whole chart?" }, { "from": "gpt", "value": "Lap." }, { "from": "human", "value": "What is the value of the largest individual bar in the whole chart?" }, { "from": "gpt", "value": "8." }, { "from": "human", "value": "Which group has the smallest summed value?" }, { "from": "gpt", "value": "Series." }, { "from": "human", "value": "What is the sum of all the values in the series group?" }, { "from": "gpt", "value": "2." }, { "from": "human", "value": "Is the value of act in tissue larger than the value of heard in loss?" }, { "from": "gpt", "value": "No." }, { "from": "human", "value": "What element does the steelblue color represent?" }, { "from": "gpt", "value": "Tissue." }, { "from": "human", "value": "What is the value of loss in award?" }, { "from": "gpt", "value": "6." }, { "from": "human", "value": "What is the label of the first group of bars from the left?" }, { "from": "gpt", "value": "Lap." }, { "from": "human", "value": "What is the label of the second bar from the left in each group?" }, { "from": "gpt", "value": "Loss." } ]
dvqa(cauldron,llava_format)
cauldron/dvqa/images/dvqa_00099882.png
[ { "from": "human", "value": "Which object is the most preferred?\nAnswer the question using a single word or phrase." }, { "from": "gpt", "value": "Beer." }, { "from": "human", "value": "Which object is the least preferred?" }, { "from": "gpt", "value": "Porch." }, { "from": "human", "value": "What percentage of people prefer the most preferred object?" }, { "from": "gpt", "value": "80." }, { "from": "human", "value": "What percentage of people prefer the least preferred object?" }, { "from": "gpt", "value": "10." }, { "from": "human", "value": "What is the difference between most and least preferred object?" }, { "from": "gpt", "value": "70." }, { "from": "human", "value": "How many objects are liked by more than 20 percent of people?" }, { "from": "gpt", "value": "Four." }, { "from": "human", "value": "Is the object beer preferred by more people than well?" }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "Are the values in the chart presented in a percentage scale?" }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "What percentage of people prefer the object porch?" }, { "from": "gpt", "value": "10." }, { "from": "human", "value": "What is the label of the second bar from the left?" }, { "from": "gpt", "value": "Plant." }, { "from": "human", "value": "Are the bars horizontal?" }, { "from": "gpt", "value": "No." } ]
dvqa(cauldron,llava_format)