Evaluation is All You Need: Strategic Overclaiming of LLM Reasoning Capabilities Through Evaluation Design
Paper
•
2506.04734
•
Published
•
21
•
3
sunlin
lincharliesun
21world's profile picture
zhaoguangxiang's profile picture
LookLikeSquareButItRectangle's profile picture
·
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
1 day ago
TriPlay-RL: Tri-Role Self-Play Reinforcement Learning for LLM Safety Alignment
authored
a paper
1 day ago
FABLE: Forest-Based Adaptive Bi-Path LLM-Enhanced Retrieval for Multi-Document Reasoning
authored
a paper
1 day ago
TriPlay-RL: Tri-Role Self-Play Reinforcement Learning for LLM Safety Alignment
Organizations
commented
2
papers
8 months ago
Update README.md
#10 opened 11 months ago
by
zhaoguangxiang
Repeated Thinking Tags in Output Generation
10
#2 opened 11 months ago
by
xldistance