Papers by Pinhuan Wang

    1 papers
    REALM: Recursive Relevance Modeling for LLM-based Document Re-Ranking (2025.emnlp-main)

    Copied to clipboard

    Challenge: Existing LLMs face ranking uncertainty, unstable top-k recovery, and high token cost due to token-intensive prompting.
    Approach: They propose a re-ranking framework that captures uncertainty and refines LLM-derived relevance through recursive Bayesian updates.
    Outcome: The proposed framework outperforms state-of-the-art re-rankers while reducing token usage and latency.

    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