深度检索：为大型语言模型逐步思考到检索

DeepRAG: Thinking to Retrieval Step by Step for Large Language Models

February 3, 2025

作者: Xinyan Guan, Jiali Zeng, Fandong Meng, Chunlei Xin, Yaojie Lu, Hongyu Lin, Xianpei Han, Le Sun, Jie Zhou

cs.AI

摘要

大型语言模型（LLMs）在推理方面表现出显著潜力，但仍然存在严重的事实幻觉问题，这是由于参数化知识的时效性、准确性和覆盖范围不足所致。同时，由于任务分解不够有效和检索冗余，推理与检索增强生成（RAG）的整合仍然具有挑战性，这可能引入噪音并降低响应质量。在本文中，我们提出了DeepRAG，这是一个将检索增强推理建模为马尔可夫决策过程（MDP）的框架，从而实现了策略性和自适应检索。通过迭代地分解查询，DeepRAG 动态确定在每一步是否检索外部知识或依赖参数化推理。实验证明，DeepRAG 提高了检索效率，同时将答案准确性提高了 21.99%，展示了其在优化检索增强推理方面的有效性。

English

Large Language Models (LLMs) have shown remarkable potential in reasoning while they still suffer from severe factual hallucinations due to timeliness, accuracy, and coverage of parametric knowledge. Meanwhile, integrating reasoning with retrieval-augmented generation (RAG) remains challenging due to ineffective task decomposition and redundant retrieval, which can introduce noise and degrade response quality. In this paper, we propose DeepRAG, a framework that models retrieval-augmented reasoning as a Markov Decision Process (MDP), enabling strategic and adaptive retrieval. By iteratively decomposing queries, DeepRAG dynamically determines whether to retrieve external knowledge or rely on parametric reasoning at each step. Experiments show that DeepRAG improves retrieval efficiency while improving answer accuracy by 21.99%, demonstrating its effectiveness in optimizing retrieval-augmented reasoning.