LARGE LANGUAGE MODELS PERFORM DIAGNOSTIC REASONING
Journal
1st Tiny Papers Track at ICLR 2023 - Tiny Papers @ ICLR 2023
Date Issued
2023-05
Author(s)
Abstract
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% comparing to standard prompting. Moreover, the gap reaches a pronounced 18% in out-domain settings. Our findings suggest expert-knowledge reasoning in large language models can be elicited through proper promptings.
Event(s)
1st Tiny Papers at 11th International Conference on Learning Representations, Tiny Papers @ ICLR 2023
Publisher
International Conference on Learning Representations, ICLR
Type
conference paper