Concept-Level Explainability for Auditing & Steering LLM Responses

Kenza Amara, Rita Sevastjanova, Mennatallah El-Assady. Concept-Level Explainability for Auditing & Steering LLM Responses. . May, 2025.

Abstract

Downloads

  • PDF
© Copyright Kenza Amara. Last updated: 2025.