FINEREASON: Evaluating and Improving LLMs' Deliberate Reasoning through Reflective Puzzle Solving
Paper
•
2502.20238
•
Published
•
23
Cunxiang Wang
wangcunxiang
·
AI & ML interests
None yet
Recent Activity
authored
a paper
3 months ago
SPaR: Self-Play with Tree-Search Refinement to Improve
Instruction-Following in Large Language Models
updated
a dataset
3 months ago
NovelQA/NovelQA
Organizations
None yet