On a synthetic benchmark of 4,290 clinical scenarios, seven LLMs often endorsed outdated advice and contradicted themselves, and combining retrieval-augmented generation with preference tuning reduced both failures.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Assessing and Mitigating Medical Knowledge Drift and Conflicts in Large Language Models
On a synthetic benchmark of 4,290 clinical scenarios, seven LLMs often endorsed outdated advice and contradicted themselves, and combining retrieval-augmented generation with preference tuning reduced both failures.