Papers with pinpoint interpretable model components

1 papers
Activation Scaling for Steering and Interpreting Language Models (2024.findings-emnlp)

Copied to clipboard

Challenge: a successful intervention should flip the correct with the wrong token, while remaining sparse.
Approach: They propose to use activation scaling to flip the correct with the wrong token . they use gradient-based optimization to learn and evaluate a specific kind of efficient intervention .
Outcome: The proposed method performs comparable with steering vectors but is much less minimal.

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