ICA-RAG: Information Completeness Guided Adaptive Retrieval-Augmented Generation for Disease Diagnosis
This addresses inefficiencies in medical diagnosis systems for clinicians, though it is incremental as it builds on existing RAG methods.
The paper tackled the problem of inefficient and noisy retrieval in Retrieval-Augmented Large Language Models for disease diagnosis by proposing ICA-RAG, which adaptively controls retrieval based on input information completeness, resulting in significant performance improvements over baselines on three Chinese electronic medical record datasets.
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.