paper-with-me

홈 › Papers

Causally Grounded Mechanistic Interpretability for LLMs with Faithful Natural-Language Explanations

2026-02-13 · Ajay Pravin Mahale arxiv

Mechanistic interpretability identifies internal circuits responsible for model behaviors, yet translating these findings into human-understandable explanations remains an open problem. We present a pipeline that bridges circuit-level analysis and natural language explanations by (i) identifying causally important attention heads via activation patching, (ii) generating explanations using both template-based and LLM-based methods, and (iii) evaluating faithfulness using ERASER-style metrics adapted for circuit-level attribution. We evaluate on the Indirect Object Identification (IOI) task in GPT-2 Small (124M parameters), identifying six attention heads accounting for 61.4% of the logit difference. Our circuit-based explanations achieve 100% sufficiency but only 22% comprehensiveness, revealing distributed backup mechanisms. LLM-generated explanations outperform template baselines by 64% on quality metrics. We find no correlation (r = 0.009) between model confidence and explanation faithfulness, and identify three failure categories explaining when explanations diverge from mechanisms.

📄 PDF Abstract BibTeX arXiv:2603.09988

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Formal Reasoning for Intelligent QA Systems: A Case Study in the Educational Domain

2025-09-15 · Tuan Bui, An Nguyen, Phat Thai, Minh Hua 외 arxiv

Reasoning is essential for closed-domain QA systems in which procedural correctness and policy compliance are critical. While large language models (LLMs) have shown strong performance on many reasoning tasks, recent wor…

Geometry-Adaptive Explainer for Faithful Dictionary-Based Interpretability under Distribution Shift

2026-05-21 · Sungjun Lim, Heedong Kim, Andrew Lee, Kyungwoo Song arxiv

Mechanistic interpretability aims to explain a model's behavior by identifying causally responsible internal structures. Dictionary-based explainers such as sparse autoencoders and transcoders are a primary tool, but the…

MechRL: Reinforcement Learning Agents Perform Circuit Discovery for Mechanistic Interpretability

2026-05-25 · Barsat Khadka arxiv

Mechanistic interpretability seeks to explain a model's behaviour by finding its circuit: the sparse subgraph of the model's computation that is causally responsible for it. Automated methods have made this search system…

Reinforcement Learning

From Mechanistic to Compositional Interpretability

2026-05-09 · Ward Gauderis, Thomas Dooms, Steven T. Homer, Kola Ayonrinde 외 arxiv

Mechanistic interpretability aims to explain neural model behaviour by reverse-engineering learned computational structure into human-understandable components. Without a formal framework, however, mechanistic explanatio…

DLM-Scope: Mechanistic Interpretability of Diffusion Language Models via Sparse Autoencoders

2026-02-05 · Xu Wang, Bingqing Jiang, Yu Wan, Baosong Yang 외 arxiv

Sparse autoencoders (SAEs) have become a standard tool for mechanistic interpretability in autoregressive large language models (LLMs), enabling researchers to extract sparse, human-interpretable features and intervene o…