English

NeuroFaith: Evaluating LLM Self-Explanation Faithfulness via Internal Representation Alignment

Computation and Language 2026-01-30 v4

Abstract

Large Language Models (LLMs) can generate plausible free text self-explanations to justify their answers. However, these natural language explanations may not accurately reflect the model's actual reasoning process, pinpointing a lack of faithfulness. Existing faithfulness evaluation methods rely primarily on behavioral tests or computational block analysis without examining the semantic content of internal neural representations. This paper proposes NeuroFaith, a flexible framework that measures the faithfulness of LLM free text self-explanation by identifying key concepts within explanations and mechanistically testing whether these concepts actually influence the model's predictions. We show the versatility of NeuroFaith across 2-hop reasoning and classification tasks. Additionally, we develop a linear faithfulness probe based on NeuroFaith to detect unfaithful self-explanations from representation space and improve faithfulness through steering. NeuroFaith provides a principled approach to evaluating and enhancing the faithfulness of LLM free text self-explanations, addressing critical needs for trustworthy AI systems.

Keywords

Cite

@article{arxiv.2506.09277,
  title  = {NeuroFaith: Evaluating LLM Self-Explanation Faithfulness via Internal Representation Alignment},
  author = {Milan Bhan and Jean-Noel Vittaut and Nicolas Chesneau and Sarath Chandar and Marie-Jeanne Lesot},
  journal= {arXiv preprint arXiv:2506.09277},
  year   = {2026}
}