Reasoning with large language models for medical question answering.
J Am Med Inform Assoc
; 31(9): 1964-1975, 2024 Sep 01.
Article
in En
| MEDLINE
| ID: mdl-38960731
ABSTRACT
OBJECTIVES:
To investigate approaches of reasoning with large language models (LLMs) and to propose a new prompting approach, ensemble reasoning, to improve medical question answering performance with refined reasoning and reduced inconsistency. MATERIALS ANDMETHODS:
We used multiple choice questions from the USMLE Sample Exam question files on 2 closed-source commercial and 1 open-source clinical LLM to evaluate our proposed approach ensemble reasoning.RESULTS:
On GPT-3.5 turbo and Med42-70B, our proposed ensemble reasoning approach outperformed zero-shot chain-of-thought with self-consistency on Steps 1, 2, and 3 questions (+3.44%, +4.00%, and +2.54%) and (2.3%, 5.00%, and 4.15%), respectively. With GPT-4 turbo, there were mixed results with ensemble reasoning again outperforming zero-shot chain-of-thought with self-consistency on Step 1 questions (+1.15%). In all cases, the results demonstrated improved consistency of responses with our approach. A qualitative analysis of the reasoning from the model demonstrated that the ensemble reasoning approach produces correct and helpful reasoning.CONCLUSION:
The proposed iterative ensemble reasoning has the potential to improve the performance of LLMs in medical question answering tasks, particularly with the less powerful LLMs like GPT-3.5 turbo and Med42-70B, which may suggest that this is a promising approach for LLMs with lower capabilities. Additionally, the findings show that our approach helps to refine the reasoning generated by the LLM and thereby improve consistency even with the more powerful GPT-4 turbo. We also identify the potential and need for human-artificial intelligence teaming to improve the reasoning beyond the limits of the model.Key words
Full text:
1
Database:
MEDLINE
Main subject:
Natural Language Processing
Limits:
Humans
Language:
En
Journal:
J Am Med Inform Assoc
Journal subject:
INFORMATICA MEDICA
Year:
2024
Type:
Article
Affiliation country:
United States