Papers by XingYu XingYu

    1 papers
    Cheems: A Practical Guidance for Building and Evaluating Chinese Reward Models from Scratch (2025.acl-long)

    Copied to clipboard

    Challenge: Existing Chinese resources are small in scale and limited to specific domains, making them insufficient for LLM post-training.
    Approach: They propose a Chinese-annotated reward model and a preference dataset to address this gap . they evaluate Chinese RMs on CheemsBench and construct an RM that captures human preferences .
    Outcome: The proposed RM achieves state-of-the-art performance on CheemsBench and CheeMePreference.

    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