Edinburgh Dataset Analytics Working Group

university

AI & ML interests

None defined yet.

Recent Activity

pminervini authored a paper 3 days ago

OpenSIR: Open-Ended Self-Improving Reasoner

pminervini authored a paper 22 days ago

Unveiling and Consulting Core Experts in Retrieval-Augmented MoE-based LLMs

pminervini authored a paper 22 days ago

PosterSum: A Multimodal Benchmark for Scientific Poster Summarization

View all activity

spaces 1

MMLU Redux EDA

models 0

None public yet

datasets 3

edinburgh-dawg/mmlu-redux-2.0

Viewer • Updated Feb 25 • 5.7k • 4.97k • 30

edinburgh-dawg/mmlu-redux

Viewer • Updated Feb 9 • 3k • 1.93k • 35

edinburgh-dawg/labelchaos

Viewer • Updated May 31, 2024 • 268k • 275