EMNLP 2024finding22 citations

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.

BibTeX
@inproceedings{nachane-etal-2024-shot,
    title = "Few shot chain-of-thought driven reasoning to prompt {LLM}s for open-ended medical question answering",
    author = "Nachane, Saeel Sandeep  and
      Gramopadhye, Ojas  and
      Chanda, Prateek  and
      Ramakrishnan, Ganesh  and
      Jadhav, Kshitij Sharad  and
      Nandwani, Yatin  and
      Raghu, Dinesh  and
      Joshi, Sachindra",
    editor = "Al-Onaizan, Yaser  and
      Bansal, Mohit  and
      Chen, Yun-Nung",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
    month = nov,
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2024.findings-emnlp.31/",
    doi = "10.18653/v1/2024.findings-emnlp.31",
    pages = "542--573"
}
Few shot chain-of-thought driven reasoning to prompt LLMs for open-ended medical question answering · EMNLP 2024