ClaimCheck：基于小语言模型的实时事实核查
ClaimCheck: Real-Time Fact-Checking with Small Language Models
AI总结：
本研究推出ClaimCheck小语言模型事实核查系统，通过复刻人类流程的模块化透明流水线，用Qwen3-4B模型在AVeriTeC数据集上达76.4%的SOTA准确率，优于更大的模型，还提供公开演示。
摘要：
我们推出ClaimCheck，这是一套由大语言模型（LLM）引导的自动事实核查系统，旨在利用实时网络证据和小语言模型验证真实世界中的主张。与依赖大型闭源模型和静态知识库的现有系统不同，ClaimCheck采用透明的分步验证流水线，复刻人类事实核查工作流程，包含网络搜索查询规划、基于网络的证据检索与摘要、证据综合与二次检索、主张判定评估四个环节。每个模块都针对小LLM做了优化，让系统能以大幅降低的算力需求实现准确且可解释的事实核查。尽管使用的是规模小得多的Qwen3-4B模型，ClaimCheck在AVeriTeC数据集上仍达到76.4%的当前最优准确率，性能优于采用LLaMA3.1 70B和GPT-4o的现有方法。大量消融实验表明，精心的模块化设计和提示策略能够弥补小LLM的能力局限。为提升可及性与透明度，我们在https://idir.uta.edu/claimcheck提供了公开演示。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
