REFINE-AF: A Task-Agnostic Framework to Align Language Models via Self-Generated Instructions using Reinforcement Learning from Automated Feedback
Paper
•
2505.06548
•
Published
•
30
Pretam Ray
Pretam
AI & ML interests
NLP
Recent Activity
liked
a dataset
4 days ago
arc-agi-community/arc-agi-2
liked
a Space
17 days ago
nanotron/ultrascale-playbook
liked
a Space
17 days ago
HuggingFaceTB/smol-training-playbook
Organizations
authored
a
paper
7 months ago