让大模型生成内容时自动查证事实并引用来源，减少幻觉。
Enhancing Factual Accuracy and Citation Generation in LLMs via Multi-Stage Self-Verification
- 分三步自我校验：验证事实、反思推理、整合引用。
- 生成内容更准确可信，且可追溯来源。
- 适合科研、新闻、法律等对准确性要求高的场景。
本研究提出 VeriFact-CoT（经验证的事实思维链）方法，旨在解决大语言模型在生成复杂事实敏感内容时普遍存在的幻觉和缺乏可信引用源问题。通过‘事实验证-反思-引用整合’的多阶段机制，该方法使大模型能够对其推理过程和最终答案进行批判性自检与修正。这一过程显著提升了生成内容的客观准确性、可信度和可追溯性，使大模型在科学研宄、新闻报道、法律咨询等高保真需求场景中更具可靠性。
原文摘要 · Abstract (English)
This research introduces VeriFact-CoT (Verified Factual Chain-of-Thought), a novel method designed to address the pervasive issues of hallucination and the absence of credible citation sources in Large Language Models (LLMs) when generating complex, fact-sensitive content. By incorporating a multi-stage mechanism of 'fact verification-reflection-citation integration,' VeriFact-CoT empowers LLMs to critically self-examine and revise their intermediate reasoning steps and final answers. This process significantly enhances the objective accuracy, trustworthiness, and traceability of the generated outputs, making LLMs more reliable for applications demanding high fidelity such as scientific research, news reporting, and legal consultation.
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。