CBR-LLM retrieves similar past driving risk cases and feeds them as few-shot examples to an LLM, improving evasive maneuver recommendations on a real near-miss dashcam dataset.
These conflicts often result from failure to yield to pedestrians by drivers or pedestrians failing to follow traffic signals
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Case-based Reasoning Augmented Large Language Model Framework for Decision Making in Realistic Safety-Critical Driving Scenarios
CBR-LLM retrieves similar past driving risk cases and feeds them as few-shot examples to an LLM, improving evasive maneuver recommendations on a real near-miss dashcam dataset.