Large Language Models Need Holistically Thought in Medical Conversational QA
This work addresses the problem of specialized medical reasoning for healthcare systems, but it is incremental as it builds on existing LLM techniques for a specific domain.
The paper tackles the challenge of improving large language models (LLMs) for medical conversational question answering (CQA) by proposing the Holistically Thought (HoT) method, which enhances response quality through diffused and focused thinking, resulting in more correct, professional, and considerate answers compared to state-of-the-art methods on three datasets.
The medical conversational question answering (CQA) system aims at providing a series of professional medical services to improve the efficiency of medical care. Despite the success of large language models (LLMs) in complex reasoning tasks in various fields, such as mathematics, logic, and commonsense QA, they still need to improve with the increased complexity and specialization of the medical field. This is because medical CQA tasks require not only strong medical reasoning, but also the ability to think broadly and deeply. In this paper, to address these challenges in medical CQA tasks that need to be considered and understood in many aspects, we propose the Holistically Thought (HoT) method, which is designed to guide the LLMs to perform the diffused and focused thinking for generating high-quality medical responses. The proposed HoT method has been evaluated through automated and manual assessments in three different medical CQA datasets containing the English and Chinese languages. The extensive experimental results show that our method can produce more correctness, professional, and considerate answers than several state-of-the-art (SOTA) methods, manifesting its effectiveness. Our code in https://github.com/WENGSYX/HoT.