Papers by Alexander Ratner

    1 papers
    Found in the middle: Calibrating Positional Attention Bias Improves Long Context Utilization (2024.findings-acl)

    Copied to clipboard

    Challenge: Large language models struggle to capture relevant information located in the middle of their input.
    Approach: They propose a calibration mechanism that allows the model to attend to contexts faithfully according to their relevance even when they are in the middle.
    Outcome: The proposed calibration mechanism mitigates this positional bias and improves retrieval-augmented generation 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