构建可解释的证据树框架，自动验证真假声明并抵御恶意生成内容干扰。
ToE: A Hierarchical and Explainable Claim Verification Framework with Dynamic Multi-source Evidence Retrieval and Aggregation
- 用动态扩展的证据树结构分解和验证每个声明，支持多源信息检索与聚合。
- 在多个数据集上相较基线提升4%至24%，对抗性伪造内容下效果更显著。
- 引入强化学习优化检索策略，理论证明其接近最优解，适合可信内容审核场景。
虚假新闻的快速传播对信息生态构成日益严重的威胁，尤其在生成式引擎优化（GEO）污染下，恶意构造的内容能被检索系统系统性地推荐，从而污染大模型推理。本文提出树状证据（ToE）框架，一种用于自动化事实核查的分层可解释推理方法，将每个声明建模为动态扩展的论证树。ToE融合强化学习驱动的多源检索代理、证据评估代理与论证树聚合算法，通过可解释的证据链迭代分解、检索与验证声明。我们进一步对检索过程提供理论分析，推导出形式化误差界，证明所学策略收敛至信息论最优策略的邻域。在多个数据集与主流大模型上的实验表明，ToE相较先进基线提升4%至24个百分点，尤其在对抗性污染输入下表现突出。
原文摘要 · Abstract (English)
The rapid spread of fake news poses increasing threats to information ecosystems, especially as AI-generated misinformation under Generative Engine Optimization (GEO) poisoning allows adversarially crafted content to be systematically surfaced by retrieval systems, contaminating LLM reasoning. In this paper, we propose Tree of Evidence (ToE), a hierarchical evidence reasoning framework for automated fact-checking that models each claim as a dynamically expanding argument tree. ToE integrates a reinforcement learning-driven multi-source retrieval agent, an evidence evaluation agent, and an argument tree aggregation algorithm to iteratively decompose, retrieve, and verify claims through an explainable evidence chain. We further provide a theoretical analysis of the retrieval process, deriving a formal error bound that guarantees the learned policy converges to a neighborhood of the information-theoretically optimal policy. Experiments across multiple datasets and backbone LLMs demonstrate that ToE achieves improvements ranging from 4 to 24 percentage points over competitive baselines, with particularly pronounced gains on adversarially poisoned inputs.
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。