Few shot chain-of-thought driven reasoning to prompt LLMs for open-ended medical question answering

Saeel Sandeep Nachane, Ojas Gramopadhye, Prateek Chanda, Ganesh Ramakrishnan, Kshitij Sharad Jadhav, Yatin Nandwani, Dinesh Raghu, Sachindra Joshi


Abstract
In this paper, we propose a modified version of the MedQA-USMLE dataset, named MEDQA-OPEN, which contains open-ended medical questions without options to mimic clinical scenarios, along with clinician-approved reasoned answers. Additionally, we implement a prompt driven by Chain of Thought (CoT) reasoning, CLINICR, to mirror the prospective process of incremental reasoning, reaching a correct response to medical questions. We empirically demonstrate how CLINICR outperforms the state-of-the-art 5-shot CoT-based prompt (Liévin et al., 2022). We also present an approach that mirrors real-life clinical practice by first exploring multiple differential diagnoses through MCQ-CLINICR and subsequently narrowing down to a final diagnosis using MCQ-ELIMINATIVE. Finally, emphasizing the importance of response verification in medical settings, we utilize a reward model mechanism, replacing the elimination process performed by MCQ-ELIMINATIVE.
Anthology ID:
2024.findings-emnlp.31
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2024
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
542–573
Language:
URL:
https://preview.aclanthology.org/build-pipeline-with-new-library/2024.findings-emnlp.31/
DOI:
10.18653/v1/2024.findings-emnlp.31
Bibkey:
Cite (ACL):
Saeel Sandeep Nachane, Ojas Gramopadhye, Prateek Chanda, Ganesh Ramakrishnan, Kshitij Sharad Jadhav, Yatin Nandwani, Dinesh Raghu, and Sachindra Joshi. 2024. Few shot chain-of-thought driven reasoning to prompt LLMs for open-ended medical question answering. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 542–573, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
Few shot chain-of-thought driven reasoning to prompt LLMs for open-ended medical question answering (Nachane et al., Findings 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/build-pipeline-with-new-library/2024.findings-emnlp.31.pdf
Software:
 2024.findings-emnlp.31.software.zip
Data:
 2024.findings-emnlp.31.data.zip