Mor Geva
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
AI×1NLP×1
Frequent co-authors
Research Timeline
2026
Can Mechanistic Interpretability Help Explain LLM Agent Failures? A Case Study on Web Element Hallucination
This paper examines the challenges of applying Mechanistic Interpretability (MI) tools to explain the decision-making processes of Large Language Model (LLM) agents in realistic scenarios.
Highlighted terms show continued research focus across papers