ReAGent: Towards A Model-agnostic Feature Attribution Method for Generative Language Models
Paper
•
2402.00794
•
Published
•
1
Interpretability XAI
-
-
Rethinking Interpretability in the Era of Large Language Models
Paper • 2402.01761 • Published • 24 -
Analyze Feature Flow to Enhance Interpretation and Steering in Language Models
Paper • 2502.03032 • Published • 60 -
Tell me why: Visual foundation models as self-explainable classifiers
Paper • 2502.19577 • Published • 11