PREreviews de “Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models”

Saltar a detalles del preprint Saltar a PREreviews

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models

por Hengyuan Zhang, Zhihao Zhang, Mingyang Wang, Zunhai Su, Yiwei Wang, Qianli Wang, Shuzhou Yuan, Ercong Nie, Xufeng Duan, Qibo Xue, Zeping Yu, Chenming Shang, Xiao Liang, Jing Xiong, Hui Shen, Chaofan Tao, Zhengwu Liu, Senjie Jin, Zhiheng Xi, Dongdong Zhang, Sophia Ananiadou, Tao Gui, Ruobing Xie, Hayden Kwok-Hay So, Hinrich Schütze, Xuanjing Huang, Qi Zhang y Ngai Wong

Publicado: 21 de enero de 2026
Servidor: Preprints.org
DOI: 10.20944/preprints202601.1663.v1

Resumen

Mechanistic Interpretability (MI) has emerged as a vital approach to demystify the opaque decision-making of Large Language Models (LLMs). However, existing reviews primarily treat MI as an observational science, summarizing analytical insights while lacking a systematic framework for actionable intervention. To bridge this gap, we present a practical survey structured around the pipeline: "Locate, Steer, and Improve." We formally categorize Localizing (diagnosis) and Steering (intervention) methods based on specific Interpretable Objects to establish a rigorous intervention protocol. Furthermore, we demonstrate how this framework enables tangible improvements in Alignment, Capability, and Efficiency, effectively operationalizing MI as an actionable methodology for model optimization. With actionable mechanistic interpretability evolving at a fast pace, we pledge to keep this survey up to date, ensuring it reflects the cutting-edge advances in this area.

Leer el preprint

0 PREreviews

Redactar una PREreview Solicitar una PREreview

PREreviews de Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models

0 PREreviews