Skip to content

@AlignRM AlignRM

Change the repository type filter

All

    Repositories list

    4 repositories

    • CheemsRM

      Public
      ACL'25: Cheems: A Practical Guidance for Building and Evaluating Chinese Reward Models from Scratch
      reinforcement-learninglarge-language-modelreward-model
      Python
      •
      Apache License 2.0
      •0•10•0•0•Updated Jun 10, 2025Jun 10, 2025

    • Critic-CoT

      Public
      Repo of the ACL'25 Findings paper "Critic-CoT: Boosting the Reasoning Abilities of Large Language Model via Chain-of-Thought Critic"
      Python
      •
      MIT License
      •0•5•0•0•Updated May 27, 2025May 27, 2025

    • RLFH

      Public
      ACL'25 Findings: On-Policy Fine-grained Knowledge Feedback for Hallucination Mitigation
      reinforcement-learninghallucinationlarge-language-model
      Python
      •
      Apache License 2.0
      •0•8•0•0•Updated May 26, 2025May 26, 2025

    • Generalizable-MM-RM

      Public
      ICML'25: The Devil Is in the Details: Tackling Unimodal Spurious Correlations for Generalizable Multimodal Reward Models
      Python
      •0•10•1•0•Updated May 19, 2025May 19, 2025