用小模型实时查证网络言论，准确率超大模型。
ClaimCheck: Real-Time Fact-Checking with Small Language Models
- 分步模拟人工核查流程，每步适配小模型。
- 仅用Qwen3-4B模型，在AVerTeC上达76.4%准确率。
- 适合关注可解释性与低成本部署的用户。
我们提出ClaimCheck，一个基于大语言模型引导的自动事实核查系统，利用实时网络证据和小型语言模型验证现实中的声明。与依赖大型封闭模型和静态知识库的以往系统不同，ClaimCheck采用透明、分步的验证流程，模仿人类核查工作流，包括网络搜索查询规划、基于网页的证据检索与摘要、证据融合与重检索，以及声明结论评估。每个模块均针对小型语言模型优化，使系统在显著降低计算成本的前提下实现高精度且可解释的核查。尽管使用的是更小的Qwen3-4B模型，ClaimCheck在AVerTeC数据集上仍达到76.4%的领先准确率，超越使用LLaMA3.1 70B和GPT-4o的先前方法。大量消融实验表明，精心设计的模块化结构与提示策略可克服小模型的局限性。为促进可访问性与透明度，我们提供了公开演示：https://idir.uta.edu/claimcheck。
原文摘要 · Abstract (English)
We introduce ClaimCheck, an LLM-guided automatic fact-checking system designed to verify real-world claims using live Web evidence and small language models. Unlike prior systems that rely on large, closed-source models and static knowledge stores, ClaimCheck employs a transparent, stepwise verification pipeline that mirrors human fact-checking workflows consisting of Web search query planning, Web-based evidence retrieval and summarization, evidence synthesis and re-retrieval, and claim verdict evaluation. Each module is optimized for small LLMs, allowing the system to deliver accurate and interpretable fact-checking with significantly lower computational requirements. Despite using a much smaller Qwen3-4B model, ClaimCheck achieves state-of-the-art accuracy of 76.4% on the AVeriTeC dataset, outperforming previous approaches using LLaMA3.1 70B and GPT-4o. Extensive ablations demonstrate that careful modular design and prompting strategies can overcome the limitations of smaller LLMs. To promote accessibility and transparency, we provide a public demo at https://idir.uta.edu/claimcheck.
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。