系统梳理RAG与推理如何减少大模型幻觉，助力真实应用落地
Mitigating Hallucination in Large Language Models (LLMs): An Application-Oriented Survey on RAG, Reasoning, and Agentic Systems
- 按知识与逻辑两类幻觉分类，分析RAG与推理的应对机制
- 提出融合RAG与推理的智能体系统统一框架，支持真实场景验证
- 面向需要高可靠性的应用开发者，如医疗、金融领域
幻觉仍是大语言模型在实际应用中可靠部署的主要障碍。检索增强生成（RAG）和推理增强成为两种最有效且广泛应用的缓解策略，标志着从单纯抑制幻觉转向创意与可靠性之间的平衡。然而，二者协同潜力及其内在机制尚未得到系统研究。本文从能力提升的应用导向出发，分析RAG、推理增强及其在智能体系统中的集成如何缓解幻觉。提出区分基于知识与基于逻辑的幻觉分类体系，系统考察RAG与推理的应对方式，并构建一个由真实应用、评估与基准支撑的统一框架。
原文摘要 · Abstract (English)
Hallucination remains one of the key obstacles to the reliable deployment of large language models (LLMs), particularly in real-world applications. Among various mitigation strategies, Retrieval-Augmented Generation (RAG) and reasoning enhancement have emerged as two of the most effective and widely adopted approaches, marking a shift from merely suppressing hallucinations to balancing creativity and reliability. However, their synergistic potential and underlying mechanisms for hallucination mitigation have not yet been systematically examined. This survey adopts an application-oriented perspective of capability enhancement to analyze how RAG, reasoning enhancement, and their integration in Agentic Systems mitigate hallucinations. We propose a taxonomy distinguishing knowledge-based and logic-based hallucinations, systematically examine how RAG and reasoning address each, and present a unified framework supported by real-world applications, evaluations, and benchmarks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。