Do Large Language Models have Shared Weaknesses in Medical Question Answering?

• Main Authors: Bean, Andrew M, Korgul, Karolina, Krones, Felix, McCraith, Robert, Mahdi, Adam
• Format: Journal Article
• Language: English
• Published: 11.10.2023
• Subjects: Computer Science - Computation and Language

Large language models (LLMs) have made rapid improvement on medical benchmarks, but their unreliability remains a persistent challenge for safe real-world uses. To design for the use LLMs as a category, rather than for specific models, requires developing an understanding of shared strengths and wea...