用多源知识实时验证大模型输出，降低幻觉率67%。
Multi-Modal Fact-Verification Framework for Reducing Hallucinations in Large Language Models
- 融合结构化数据库、网页搜索与学术文献进行交叉验证
- 测试中幻觉率降低67%，专家满意率达89%
- 适合医疗、金融等对准确性要求高的场景
大型语言模型在交互式AI系统中已带来变革，但其存在严重缺陷：会自信地生成看似合理却虚假的信息。这种幻觉问题已成为真实应用中准确性的主要障碍。我们开发了一种事实验证框架，通过交叉比对大模型输出与多种知识来源，在生成时实时发现并纠正错误。系统整合结构化数据库、实时网络搜索和学术文献，一旦检测到不一致，自动修正内容并保持响应自然流畅。跨多个领域的测试表明，该方法可将幻觉率降低67%，且不损害响应质量。医疗、金融及科研领域的专家对修正后的输出评价满意度达89%，显著优于未经验证的原始输出。本工作为高精度应用场景提供了实用可信的解决方案。
原文摘要 · Abstract (English)
While Large Language Models have transformed how we interact with AI systems, they suffer from a critical flaw: they confidently generate false information that sounds entirely plausible. This hallucination problem has become a major barrier to deploying these models in real-world applications where accuracy matters. We developed a fact verification framework that catches and corrects these errors in real-time by cross checking LLM outputs against multiple knowledge sources. Our system combines structured databases, live web searches, and academic literature to verify factual claims as they're generated. When we detect inconsistencies, we automatically correct them while preserving the natural flow of the response. Testing across various domains showed we could reduce hallucinations by 67% without sacrificing response quality. Domain experts in healthcare, finance, and scientific research rated our corrected outputs 89% satisfactory a significant improvement over unverified LLM responses. This work offers a practical solution for making LLMs more trustworthy in applications where getting facts wrong isn't an option.
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。