作者位次 #3/4ACL 2026Findings· Findings of ACL
DRIV - EX : Counterfactual Explanations for Driving LLM s
Amaia Cardiel · Eloi Zablocki · Elias Ramzi · Eric Gaussier
摘要
Large language models (LLMs) are increasingly used as reasoning engines in autonomous driving, yet their decision-making remains opaque. We propose to study their decision process through counterfactual explanations, which identify the minimal semantic changes to a scene description required to a...