作者位次 #2/5ACL 2026Poster· Natural Language Processing
DEFT : Demystifying VLN Failures via a Unified Dual-View Explainability Framework for LLM -based Agents
Yawen Wang · Yihan Dai · Jianming Chen · Junjie Wang · Qing Wang
摘要
Large Language Models (LLMs) have emerged as central planners in Vision-and-Language Navigation (VLN), yet their complexity increasingly obscures their internal decision-making. Existing interpretability methods typically isolate temporal criticality from feature salience, creating an alignment g...