Reproduce “Bias Fitting to Mitigate Length Bias of Reward Model in RLHF” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Kangwen Zhao, Jianfeng Cai, Jinhua Zhu, Ruopei Sun, Dongyun Xue, Wengang Zhou, Li Li, Houqiang Li
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.