TC-RAG:Turing-Complete RAG's Case study on Medical LLM Systems

TL;DR

This paper introduces TC-RAG, a Turing-Complete Retrieval-Augmented Generation framework that enhances medical LLMs by improving retrieval control, accuracy, and knowledge management, demonstrated through real-world healthcare dataset experiments.

Contribution

The paper presents a novel Turing-Complete system for RAG that manages system state variables, enabling adaptive retrieval, controlled halting, and error mitigation in medical LLM applications.

Findings

Over 7.20% accuracy improvement over existing methods

Effective management of retrieval processes via memory stack system

Enhanced control over knowledge retrieval and error reduction

Abstract

In the pursuit of enhancing domain-specific Large Language Models (LLMs), Retrieval-Augmented Generation (RAG) emerges as a promising solution to mitigate issues such as hallucinations, outdated knowledge, and limited expertise in highly specialized queries. However, existing approaches to RAG fall short by neglecting system state variables, which are crucial for ensuring adaptive control, retrieval halting, and system convergence. In this paper, we introduce the TC-RAG through rigorous proof, a novel framework that addresses these challenges by incorporating a Turing Complete System to manage state variables, thereby enabling more efficient and accurate knowledge retrieval. By leveraging a memory stack system with adaptive retrieval, reasoning, and planning capabilities, TC-RAG not only ensures the controlled halting of retrieval processes but also mitigates the accumulation of erroneous knowledge via Push and Pop actions. In the case study of the medical domain, our extensive experiments on real-world healthcare datasets demonstrate the superiority of TC-RAG over existing methods in accuracy by over 7.20\%. Our dataset and code have been available at https://https://github.com/Artessay/SAMA.git.