BianQue: Balancing the Questioning and Suggestion Ability of Health LLMs with Multi-turn Health Conversations Polished by ChatGPT

This article discusses the limitations of Large Language Models (LLMs) in providing personalized health suggestions due to their inability to engage in multi-turn questioning. To address this, the authors propose BianQue, a ChatGLM-based LLM that’s finetuned with a self-constructed health conversation dataset. BianQue can balance the capabilities of both questioning and health suggestions, which is expected to advance the research and application of LLMs in proactive health.

Publication date: 26 Oct 2023
Project Page: https://github.com/scutcyr/BianQue
Paper: https://arxiv.org/pdf/2310.15896