机制可解释性能否解释LLM智能体失败?以网页元素幻觉为例
Can Mechanistic Interpretability Help Explain LLM Agent Failures? A Case Study on Web Element Hallucination
Mohamed Aghzal, Mor Geva, Gregory J. Stein, Ziyu Yao
AI 速读 基于摘要
该案例研究将机制可解释性工具用于分析网页智能体的元素幻觉,发现线性探针可预测并部分纠正幻觉,但解释效果受提示格式和计算分布性限制。
cs.AI · cs.CL
查看原文摘要
Mechanistic Interpretability (MI) has made significant progress in explaining the internal computations of Large Language Models (LLMs); however, these advances have yet to demonstrate comparable success in explaining the decision-making processes of LLM-based agents. This paper examines the challenges MI tools face when applied to realistic agentic failures. We focus on one such failure: web agents hallucinating actions that are not available on a website. We apply a series of mechanistic analyzes to Qwen2.5-7B-Instruct as it interacts with live websites. We find that a linear probe trained on the last prompt token can predict hallucinations before generation begins (0.80 AUC) and steering along a probe direction corrects 85\% of hallucinations, but disrupts 7\% of valid actions. However, these results only provide a partial explanation of why the agent hallucinates. The probe direction is sensitive to prompt formatting, losing much of its steering effect after a minor change to how actions are represented. Additionally, circuit identification can be difficult as the computation is distributed across multiple components and positions, and the information the agent relies on varies across examples. We discuss how these observations challenge the assumptions underlying standard MI methods for circuit discovery and feature identification, and outline future directions for making these methods better suited to explain failures in LLM-based agents.