Healthcare agent: eliciting the power of large language models for medical consultation by Zhiyao Ren & Yibing Zhan & Baosheng Yu & Liang Ding & Pingbo Xu & Dacheng Tao instant download

Healthcare agent: eliciting the power of large language models for medical consultation by Zhiyao Ren & Yibing Zhan & Baosheng Yu & Liang Ding & Pingbo Xu & Dacheng Tao instant download

Large language models (LLMs) have achieved remarkable success across many fields but facechallenges in complex real-world scenarios like medical consultation, particularly regarding inquiry1234567890():,;1234567890():,;quality and safety concerns. In this paper, we introduce a healthcare agent designed to address theseissues, which cannot be fully resolved through a vanilla one-time fine-tuning process. The healthcareagent includes three components: a dialogue component for planning safe and effectiveconversations, a memory component for storing patient conversations and medical history, and aprocessing component for report generation. To evaluate our healthcare agent’s performance inmedical consultations, we employ both expert assessment from medical professionals and anautomated evaluation system powered by ChatGPT for large-scale testing. Our results demonstratethat the healthcare agent significantly enhances the capabilities of general LLMs in medicalconsultations, particularly in inquiry quality, response quality, and safety. Through extensive ablationstudies, we also analyze the impact of each component.