arXiv:2506.09277

Did I Faithfully Say What I Thought? Bridging the Gap Between Neural Activity and Self-Explanations in Large Language Models

Milan Bhan, Jean-Noel Vittaut, Nicolas Chesneau, Sarath Chandar, Marie-Jeanne Lesot

제출 2025-06-10

원문 초록

Large Language Models (LLM) have demonstrated the capability of generating free text self Natural Language Explanation (self-NLE) to justify their answers. Despite their logical appearance, self-NLE do not necessarily reflect the LLM actual decision-making process, making such explanations unfaithful. While existing methods for measuring self-NLE faithfulness mostly rely on behavioral tests or computational block identification, none of them examines the neural activity underlying the model's reasoning. This work introduces a novel flexible framework for quantitatively measuring the faithfulness of LLM-generated self-NLE by directly comparing the latter with interpretations of the model's internal hidden states. The proposed framework is versatile and provides deep insights into self-NLE faithfulness by establishing a direct connection between self-NLE and model reasoning. This approach advances the understanding of self-NLE faithfulness and provides building blocks for generating more faithful self-NLE.

함께 살펴볼 논문

공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.

토론

이 논문과 연결된 포럼 글이 아직 없습니다.