用多工具智能体动态查证假信息，让判断过程可追溯、抗篡改。
Toward Verifiable Misinformation Detection: A Multi-Tool LLM Agent Framework
- 构建三工具智能体：精准搜索、信源可信度评估、数值命题验证
- 在FakeNewsNet上准确率超基线模型，且对改写内容仍保持鲁棒性
- 适合需要高透明度与可验证性的事实核查场景，如新闻审核
随着大语言模型的普及，虚假信息检测变得愈发重要且复杂。本文提出一种创新的可验证假信息检测智能体，超越传统的真/假二元判断。该智能体通过动态交互多样网络资源主动验证主张，评估信息来源可信度，综合证据并提供完整可追溯的推理过程。设计的智能体架构包含三个核心工具：精确网页搜索工具、信源可信度评估工具和数值命题验证工具，支持多步验证策略，保留证据日志，形成全面评估结论。在FakeNewsNet等标准假信息数据集上进行评估，对比传统机器学习模型与大模型。评估指标包括标准分类性能、推理过程质量以及对改写内容的鲁棒性测试。实验结果表明，该智能体在假信息检测准确率、推理透明度及抗信息重写能力方面均优于基线方法，为可信人工智能辅助事实核查提供了新范式。
原文摘要 · Abstract (English)
With the proliferation of Large Language Models (LLMs), the detection of misinformation has become increasingly important and complex. This research proposes an innovative verifiable misinformation detection LLM agent that goes beyond traditional true/false binary judgments. The agent actively verifies claims through dynamic interaction with diverse web sources, assesses information source credibility, synthesizes evidence, and provides a complete verifiable reasoning process. Our designed agent architecture includes three core tools: precise web search tool, source credibility assessment tool and numerical claim verification tool. These tools enable the agent to execute multi-step verification strategies, maintain evidence logs, and form comprehensive assessment conclusions. We evaluate using standard misinformation datasets such as FakeNewsNet, comparing with traditional machine learning models and LLMs. Evaluation metrics include standard classification metrics, quality assessment of reasoning processes, and robustness testing against rewritten content. Experimental results show that our agent outperforms baseline methods in misinformation detection accuracy, reasoning transparency, and resistance to information rewriting, providing a new paradigm for trustworthy AI-assisted fact-checking.
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。