用特定上下文知识增强大语言模型以缓解中小企业的错误信息：一种基于RAG的建模与分析
Enhancing LLMs with Context-Specific Knowledge for Mitigating Misinformation in SMEs: A RAG-based Modeling and Analysis
浏览论文内容
中文总结 AI 辅助
该研究针对中小企业使用LLM时面临的错误信息问题，提出VectorRAG与GraphRAG方法，在LLaMA等模型上验证RAG可提升响应质量，助力可靠决策。
中文摘要 AI 辅助
大语言模型（LLMs）作为人工智能（AI）的一部分，正被中小企业（SMEs）越来越多地采用，以增强问答能力并支持业务决策流程。然而，LLM生成内容中的幻觉可能成为错误信息的来源，降低中小企业用户对其可靠性和可信度的信心。检索增强生成（RAG）已成为应对这一挑战的有前景的方法，通过将外部知识源融入建模过程来实现。本文提出VectorRAG和GraphRAG两种建模方法以缓解幻觉和错误信息风险，并在中小企业环境中评估其有效性。我们在多个最先进的LLM（包括LLaMA、Mistral和Qwen）上进行实验评估，从有用响应生成、幻觉风险、上下文相关性及人工可解释性等方面评估性能。结果表明，经RAG增强的LLMs可通过减少幻觉和错误信息显著提升响应质量，从而支持中小企业环境中更可靠、可信且具有上下文感知的决策。
英文摘要
Large Language Models (LLMs), a part of artificial intelligence (AI), are increasingly being adopted by Small and Medium Enterprises (SMEs) to enhance question-answering capabilities and support business decision-making processes. However, hallucinations in LLM-generated outputs can serve as a source of misinformation, reducing user confidence in their reliability and trustworthiness within SMEs. Retrieval-Augmented Generation (RAG) has emerged as a promising approach to address this challenge by incorporating external knowledge sources into the modeling process. In this paper, we present VectorRAG and GraphRAG modeling approaches to mitigate hallucinations and misinformation risks and evaluate their effectiveness in SME environments. Our experimental evaluation is conducted on multiple state-of-the-art LLMs, including LLaMA, Mistral, and Qwen, to assess performance in terms of useful response generation, risk of hallucination, contextual relevance, as well as human-interpretation. The results demonstrate that RAG-enhanced LLMs can significantly improve response quality by reducing hallucinations and misinformation, thereby supporting more reliable, trustworthy, and context-aware decision-making in SME environments.
发表机构
- School of Science, Edith Cowan University（伊迪斯科文大学理学院）
机构由 AI 辅助整理，请以论文原文为准。
