Large Language Models Perform Diagnostic Reasoning

07/18/2023
by   Cheng-Kuang Wu, et al.
0

We explore the extension of chain-of-thought (CoT) prompting to medical reasoning for the task of automatic diagnosis. Motivated by doctors' underlying reasoning process, we present Diagnostic-Reasoning CoT (DR-CoT). Empirical results demonstrate that by simply prompting large language models trained only on general text corpus with two DR-CoT exemplars, the diagnostic accuracy improves by 15 pronounced 18 reasoning in large language models can be elicited through proper promptings.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset