arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2408.09199cs.IR
收藏

TC-RAG:图灵完备检索增强生成在医疗大语言模型系统上的案例研究

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

Peking University(北京大学);City University of Hong Kong (Dongguan)(香港城市大学(东莞));University of Chinese Academy of Sciences(中国科学院大学);ShanghaiTech University(上海科技大学);University of Electronic Science and Technology of China(电子科技大学)

Xinke Jiang, Yue Fang, Rihong Qiu, Haoyu Zhang, Yongxin Xu, Hao Chen, Wentao Zhang, Ruizhe Zhang, Yuchen Fang, Xinyu Ma, Xu Chu, Junfeng Zhao, Yasha Wang

AI总结:

本文提出融入图灵完备系统的TC-RAG框架,经医疗领域案例研究,其在真实医疗数据集上的准确率较现有方法提升超7.20%,可缓解RAG的状态变量缺失等问题。

摘要:

为提升领域专用大语言模型(LLM)性能,检索增强生成(RAG)是缓解幻觉、知识过时及专业查询能力有限等问题的有前景方案。但现有RAG方法忽略系统状态变量,而该变量对自适应控制、检索中止及系统收敛至关重要。本文引入TC-RAG,该框架经严格证明,通过融入图灵完备系统管理状态变量以应对上述挑战,实现更高效准确的知识检索。TC-RAG利用具备自适应检索、推理与规划能力的内存栈系统,既确保检索过程的受控中止,又通过压栈(Push)与弹栈(Pop)操作减少错误知识累积。在医疗领域案例研究中,对真实医疗数据集的大量实验表明,TC-RAG在准确率上较现有方法提升超7.20%。本文数据集与代码已发布于https://github.com/Artessay/SAMA.git。

英文摘要:

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(LLMs), Retrieval-Augmented Generation (RAG) emerges as a promising solution to mitigate issues such as hallucinations, outdated knowledge, and limited expertise in highly specialized queries.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://github.com/Artessay/TC-RAG .

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。

↑