系统梳理大模型事实性评估难题与验证方法
Hallucination to Truth: A Review of Fact-Checking and Factuality Evaluation in Large Language Models
- 从幻觉、数据集局限等角度分析事实性评估挑战
- 指出现有评估指标不足，强调外部证据验证的重要性
- 适合关注大模型可信度与事实一致性的研究者
大型语言模型（LLMs）在包含错误或误导性内容的海量互联网语料上训练，易生成虚假信息，因此稳健的事实核查至关重要。本文系统分析了如何评估LLM生成内容的真实性，探讨了幻觉、数据集局限性和评估指标可靠性等关键挑战。强调需构建融合先进提示策略、领域特定微调和检索增强生成（RAG）的强健事实核查框架。提出五个研究问题，引导对2020至2025年相关文献的分析，涵盖评估方法与缓解技术。还回顾了指令微调、多智能体推理及RAG框架中的外部知识获取机制。关键发现包括：当前评估指标存在局限，验证过的外部证据至关重要，通过领域定制可显著提升事实一致性。本文强调需构建更准确、可解释且上下文感知的事实核查体系，推动可信模型的发展。
原文摘要 · Abstract (English)
Large Language Models (LLMs) are trained on vast and diverse internet corpora that often include inaccurate or misleading content. Consequently, LLMs can generate misinformation, making robust fact-checking essential. This review systematically analyzes how LLM-generated content is evaluated for factual accuracy by exploring key challenges such as hallucinations, dataset limitations, and the reliability of evaluation metrics. The review emphasizes the need for strong fact-checking frameworks that integrate advanced prompting strategies, domain-specific fine-tuning, and retrieval-augmented generation (RAG) methods. It proposes five research questions that guide the analysis of the recent literature from 2020 to 2025, focusing on evaluation methods and mitigation techniques. Instruction tuning, multi-agent reasoning, and RAG frameworks for external knowledge access are also reviewed. The key findings demonstrate the limitations of current metrics, the importance of validated external evidence, and the improvement of factual consistency through domain-specific customization. The review underscores the importance of building more accurate, understandable, and context-aware fact-checking. These insights contribute to the advancement of research toward more trustworthy models.
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。