ICA-RAG：信息完整性引导的自适应检索增强生成用于疾病诊断
ICA-RAG: Information Completeness Guided Adaptive Retrieval-Augmented Generation for Disease Diagnosis
AI总结：
针对现有RAG方法在疾病诊断中检索策略不灵活的问题，提出ICA-RAG框架，通过信息完整性引导的自适应控制模块优化检索并过滤知识，在三个中文电子病历数据集上显著优于基线方法。
摘要：
检索增强大语言模型（LLMs）通过整合外部知识，在包括临床诊断在内的医学领域展现了卓越的性能。然而，现有的RAG方法往往难以根据诊断难度和输入样本的信息量来调整检索策略。这一局限性导致过度且往往不必要的检索，损害了计算效率，并增加了引入噪声的风险，从而可能降低诊断准确性。为解决这一问题，我们提出了ICA-RAG（信息完整性引导的自适应检索增强生成），一种用于增强疾病诊断中RAG可靠性的新型框架。ICA-RAG利用自适应控制模块，基于输入的信息完整性来评估检索的必要性。通过优化检索并结合知识过滤，ICA-RAG使检索操作更好地与临床需求对齐。在三个中文电子病历数据集上的实验表明，ICA-RAG显著优于基线方法，突显了其在临床诊断中的有效性。
英文摘要：
Retrieval-Augmented Large Language Models (LLMs), which integrate external knowledge, have shown remarkable performance in medical domains, including clinical diagnosis. However, existing RAG methods often struggle to tailor retrieval strategies to diagnostic difficulty and input sample informativeness. This limitation leads to excessive and often unnecessary retrieval, impairing computational efficiency and increasing the risk of introducing noise that can degrade diagnostic accuracy. To address this, we propose ICA-RAG (\textbf{I}nformation \textbf{C}ompleteness Guided \textbf{A}daptive \textbf{R}etrieval-\textbf{A}ugmented \textbf{G}eneration), a novel framework for enhancing RAG reliability in disease diagnosis. ICA-RAG utilizes an adaptive control module to assess the necessity of retrieval based on the input's information completeness. By optimizing retrieval and incorporating knowledge filtering, ICA-RAG better aligns retrieval operations with clinical requirements. Experiments on three Chinese electronic medical record datasets demonstrate that ICA-RAG significantly outperforms baseline methods, highlighting its effectiveness in clinical diagnosis.
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。
