"length bias mitigation" Papers
2 papers found
Earlier Tokens Contribute More: Learning Direct Preference Optimization From Temporal Decay Perspective
Ruichen Shao, Bei Li, Gangao Liu et al.
ICLR 2025oralarXiv:2502.14340
7
citations
WildBench: Benchmarking LLMs with Challenging Tasks from Real Users in the Wild
Bill Yuchen Lin, Yuntian Deng, Khyathi Chandu et al.
ICLR 2025posterarXiv:2406.04770
142
citations