基于LLM的医疗助手个性化：短期与长期记忆协同
LLM-based Medical Assistant Personalization with Short- and Long-Term Memory Coordination
AI总结：
针对基于LLM的个性化医疗助手研究不足、全量训练成本高昂的问题，本文提出融合PEFT方案的新型计算仿生记忆机制，通过协调短期与长期记忆实现医疗助手个性化。
摘要：
诸如GPT3.5之类的大语言模型（LLM）在理解和生成自然语言方面已展现出卓越能力。另一方面，医疗助手有潜力为个人带来显著益处。然而，对基于LLM的个性化医疗助手的探索仍相对较少。通常，患者会根据自身背景和偏好以不同方式交谈，这就需要完成增强面向用户的医疗助手这一任务。虽然可以为此目标全面训练一个LLM，但其资源消耗令人难以承受。先前研究已探索基于记忆的方法，以便在对话会话中处理新查询时，结合对先前错误的认知来增强响应。我们认为，仅有记忆模块并不充分，而全面训练LLM又可能成本过高。在本研究中，我们提出一种新颖的计算仿生记忆机制，并配备参数高效微调（PEFT）方案，以实现医疗助手的个性化。
英文摘要：
Large Language Models (LLMs), such as GPT3.5, have exhibited remarkable proficiency in comprehending and generating natural language. On the other hand, medical assistants hold the potential to offer substantial benefits for individuals. However, the exploration of LLM-based personalized medical assistant remains relatively scarce. Typically, patients converse differently based on their background and preferences which necessitates the task of enhancing user-oriented medical assistant. While one can fully train an LLM for this objective, the resource consumption is unaffordable. Prior research has explored memory-based methods to enhance the response with aware of previous mistakes for new queries during a dialogue session. We contend that a mere memory module is inadequate and fully training an LLM can be excessively costly. In this study, we propose a novel computational bionic memory mechanism, equipped with a parameter-efficient fine-tuning (PEFT) schema, to personalize medical assistants.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
