Papers by Sam Pan

    1 papers
    COSMIC: Generalized Refusal Direction Identification in LLM Activations (2025.findings-acl)

    Copied to clipboard

    Challenge: Existing methods depend on predefined refusal templates detectable in output tokens or manual review.
    Approach: They propose a framework that optimally identifies steering directions and target layers using cosine similarity, entirely independent of output text.
    Outcome: The proposed framework achieves comparable steering effectiveness without any prior knowledge or assumptions of a model’s refusal behavior such as the use of certain refusal tokens.

    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