用树状结构规划验证步骤，提升假信息检测准确率。
Trification: A Comprehensive Tree-based Strategy Planner and Structural Verification for Fact-Checking
- 构建依赖图规划验证动作，确保覆盖所有Claim组件
- 动态调整验证策略，实现逻辑自洽的最终判断
- 在两个基准上超越现有方法，适合可信内容审核场景
技术进步使信息可一键传播，虚假信息快速扩散。自动化事实核查系统因此成为保障网络生态安全的关键。现有方法虽通过分解命题并利用大模型多智能体执行验证取得成效，但仍存在两大缺陷：难以验证命题中每个成分，且缺乏结构化框架连接子任务结果以做出最终判断。本文提出新型自动核查框架Trification，首先生成全面的验证动作集，确保命题完整覆盖；再将这些动作结构化为依赖图，建模动作间的逻辑关系；该图支持动态调整，使系统可自适应优化验证策略。在两个挑战性基准上的实验表明，本框架显著提升核查准确率，推动了自动化事实核查技术的发展。
原文摘要 · Abstract (English)
Technological advancement allows information to be shared in just a single click, which has enabled the rapid spread of false information. This makes automated fact-checking system necessary to ensure the safety and integrity of our online media ecosystem. Previous methods have demonstrated the effectiveness of decomposing the claim into simpler sub-tasks and utilizing LLM-based multi agent system to execute them. However, those models faces two limitations: they often fail to verify every component in the claim and lack of structured framework to logically connect the results of sub-tasks for a final prediction. In this work, we propose a novel automated fact-checking framework called Trification. Our framework begins by generating a comprehensive set of verification actions to ensure complete coverage of the claim. It then structured these actions into a dependency graph to model the logical interaction between actions. Furthermore, the graph can be dynamically modified, allowing the system to adapt its verification strategy. Experimental results on two challenging benchmarks demonstrate that our framework significantly enhances fact-checking accuracy, thereby advancing current state-of-the-art in automated fact-checking system.
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。