面向医疗保健中私有数据处理的检索增强思维过程
Retrieval Augmented Thought Process for Private Data Handling in Healthcare
AI总结：
本文提出检索增强思维过程（RATP），将LLM思维生成建模为多步决策过程，结合蒙特卡洛树搜索与代理奖励函数，在私有电子病历问答任务上相比上下文检索增强生成提升35%准确率。
摘要：
大型语言模型（LLMs）已展现出凭借其广泛的医学知识辅助临床医生和公众的强大潜力。然而，由于对训练所用数据隐私的担忧，它们在医疗保健中的应用受到限制，因为安全和伦理问题阻碍了私有和个人信息的整合。此外，即使能够通过信息检索增强其能力以获取最新知识，当前LLMs与信息检索的集成对不完美检索缺乏鲁棒性，这可能妨碍其有效性，甚至降低整体性能。在本工作中，我们通过引入检索增强思维过程（RATP）来应对这一挑战。在可访问外部知识的前提下，RATP将LLMs的思维生成形式化为一个多步骤决策过程。为优化这一思维过程，RATP利用蒙特卡洛树搜索，并学习一个代理奖励函数，从而实现成本高效的推理。在一个被刻意排除在任何LLM训练集之外的电子病历私有数据集上，RATP在问答任务中相比上下文检索增强生成实现了35%的额外准确率提升。
英文摘要：
Large Language Models (LLMs) have demonstrated the strong potential to assist both clinicians and the general public with their extensive medical knowledge. However, their application in healthcare is constrained due to concerns about the privacy of data used in training, which prevents the integration of private and personal information because of security and ethical issues. Moreover, if their capabilities can be enhanced with information retrieval to access up-to-date knowledge, the current integration of LLMs with Information retrieval lacks robustness to imperfect retrieval, which can hinder their effectiveness and even reduce overall performance. In this work, we address this challenge by introducing the Retrieval-Augmented Thought Process (RATP). Given access to external knowledge, RATP formulates the thought generation of LLMs as a multiple-step decision process. To optimise such a thought process, RATP leverages Monte-Carlo Tree Search and learns a proxy reward function that permits cost-efficient inference. On a private dataset of electronic medical records, deliberately excluded from any LLM training set, RATP achieves 35% additional accuracy compared to in-context retrieval-augmented generation for the question-answering task.
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。
