Trification: A Comprehensive Tree-based Strategy Planner and Structural Verification for Fact-Checking

2025-11-28

AI Summary

Existing automated fact-checking systems struggle to comprehensively verify all components of a claim and lack structured mechanisms to integrate subtask outcomes for final judgment. To address this, we propose TreeFC: a tree-structured multi-agent fact-checking framework. It employs an LLM-driven tree planner to generate a set of verification actions covering all claim constituents and constructs a dynamically adjustable dependency graph to model logical relationships among subtasks. Our core contribution is the explicit structuralization of the verification process into a hierarchical, interpretable tree-based reasoning path—ensuring completeness guarantees and enabling dynamic strategy adaptation. Evaluated on two challenging benchmarks—FEVEROUS and SciFact—TreeFC achieves substantial accuracy improvements over prior methods, establishing new state-of-the-art performance.

Technology Category

• Natural Language Processing: Fact-Checking / Misinformation Detection (NLP Focus)
• Constraint Satisfaction and Optimization: Satisfiability Modulo Theories
• Multiagent Systems: Agreement, Argumentation & Negotiation

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

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.

Problem

• Ensures complete verification of all claim components
• Models logical interactions between verification sub-tasks
• Dynamically adapts verification strategy for accuracy

Innovation

• Generates comprehensive verification actions for claim coverage
• Structures actions into a dependency graph for logical interaction
• Dynamically modifies graph to adapt verification strategy