arXiv · 2307.08922
Large Language Models Perform Diagnostic Reasoning
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.
Explore related subjects
Keep this discovery
Cheng-Kuang Wu, Wei-Lin Chen, Hsin-Hsi Chen. 2023-07-18. Large Language Models Perform Diagnostic Reasoning. https://arxiv.org/abs/2307.08922
Cite the original work for its findings. Save a collection to share your selection of sources.