Research papers · Posted 2025.06.25 · Preprint
Case-based Reasoning Augmented Large Language Model Framework for Decision Making in Realistic Safety-Critical Driving Scenarios
Case-based Reasoning Augmented Large Language Model Framework for Decision Making in Realistic Safety-Critical Driving Scenarios
Overview
CBR-LLM combines dashcam scene understanding with retrieval of relevant past cases for evasive-maneuver recommendations. Experiments compare decision quality, explanations and alignment with experts across language models and risk-aware prompting strategies.
Author-supplied source information
Author-supplied information on arXiv.
12 pages, 10 figures, under-review conference
Version: v1