Papers with debiased reward model

    1 papers
    Bias Fitting to Mitigate Length Bias of Reward Model in RLHF (2026.acl-long)

    Copied to clipboard

    Challenge: Existing approaches to tackling length bias are limited by their complexity or lack of a linear length-reward relation.
    Approach: They propose a framework that learns and corrects underlying bias patterns by fitting a length-reward relationship into a reward model.
    Outcome: The proposed framework improves length-controlled win rate and reduces verbosity without compromising performance.

    What is GenGO?

    GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

    Information

    About
    Limitations