Diagnostic reasoning prompts reveal the potential for large language model interpretability in medicine
Abstract One of the major barriers to using large language models (LLMs) in medicine is the perception they use uninterpretable methods to make clinical decisions that are inherently different from the cognitive processes of clinicians. In this manuscript we develop diagnostic reasoning prompts to s...
Main Authors: | Thomas Savage, Ashwin Nayak, Robert Gallo, Ekanath Rangan, Jonathan H. Chen |
---|---|
Format: | Article |
Language: | English |
Published: |
Nature Portfolio
2024-01-01
|
Series: | npj Digital Medicine |
Online Access: | https://doi.org/10.1038/s41746-024-01010-1 |
Similar Items
-
Prompt Optimization in Large Language Models
by: Antonio Sabbatella, et al.
Published: (2024-03-01) -
Large Language Models and Logical Reasoning
by: Robert Friedman
Published: (2023-05-01) -
Response Generated by Large Language Models Depends on the Structure of the Prompt
by: Pradosh Kumar Sarangi, et al. -
Prompt Engineering: Guiding the Way to Effective Large Language Models
by: Mohammad Aljanabi, et al.
Published: (2023-11-01) -
Predictive Prompts with Joint Training of Large Language Models for Explainable Recommendation
by: Ching-Sheng Lin, et al.
Published: (2023-10-01)