AI RESEARCH
DRIV-EX: Counterfactual Explanations for Driving LLMs
arXiv CS.CL
•
ArXi:2603.00696v2 Announce Type: replace 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 alter a driving plan. Evaluated using the LC-LLM planner on a textual transcription of the highD dataset, DRIV-EX generates valid, fluent counterfactuals reliably than existing baselines.