ART: Adaptive Reasoning Trees for Explainable Claim Verification

2026-01-09

arXiv.org

AI Summary

This work addresses the challenge of establishing trustworthiness in high-stakes fact-checking with large language models, where opacity and lack of contestability often undermine reliability. To this end, the paper proposes Adaptive Reasoning Trees (ART), introducing a novel, contestable hierarchical argumentation mechanism. ART constructs tree-structured arguments comprising supporting and rebutting sub-claims, which are then evaluated through pairwise, bottom-up comparisons by a referee large language model to produce transparent and verifiable reasoning paths. This approach overcomes the limitations of traditional chain-of-thought reasoning by enabling structured, multi-perspective deliberation. Experimental results demonstrate that ART consistently outperforms strong baselines across multiple benchmark datasets, setting a new standard for interpretable and reliable fact-checking systems.

Technology Category

• Knowledge Representation and Reasoning: Argumentation
• Natural Language Processing: Fact-Checking / Misinformation Detection (NLP Focus)
• Reasoning under Uncertainty: Other Foundations of Reasoning under Uncertainty

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Large Language Models (LLMs) are powerful candidates for complex decision-making, leveraging vast encoded knowledge and remarkable zero-shot abilities. However, their adoption in high-stakes environments is hindered by their opacity; their outputs lack faithful explanations and cannot be effectively contested to correct errors, undermining trustworthiness. In this paper, we propose ART (Adaptive Reasoning Trees), a hierarchical method for claim verification. The process begins with a root claim, which branches into supporting and attacking child arguments. An argument's strength is determined bottom-up via a pairwise tournament of its children, adjudicated by a judge LLM, allowing a final, transparent and contestable verdict to be systematically derived which is missing in methods like Chain-of-Thought (CoT). We empirically validate ART on multiple datasets, analyzing different argument generators and comparison strategies. Our findings show that ART's structured reasoning outperforms strong baselines, establishing a new benchmark for explainable claim verification which is more reliable and ensures clarity in the overall decision making step.

Problem

• explainable AI
• claim verification
• trustworthiness
• reasoning transparency
• large language models

Innovation

• Adaptive Reasoning Trees
• Explainable Claim Verification
• Hierarchical Argumentation
• Contestable AI
• LLM-based Reasoning