Open access
Jul 2026
Do large language models differ in their pharmacology-related response quality for oral and maxillofacial surgery? a blinded expert benchmark study.
Current LLMs should be regarded as adjunctive tools requiring expert verification for high-risk OMFS pharmacological decisions, as positive correlations among the evaluation criteria within the ChatGPT data indicated convergence among the three scoring dimensions.
Mustafa Isleyen, Asenur Aydemir
· BMC Oral Health · 0 citations