ART: Adaptive Reasoning Trees for Explainable Claim Verification
This addresses the need for trustworthy AI in high-stakes environments by providing a more reliable and clear decision-making process, though it is incremental as it builds on existing LLM capabilities.
The paper tackles the problem of opaque decision-making in Large Language Models for high-stakes claim verification by proposing ART, a hierarchical method that uses adaptive reasoning trees to generate transparent and contestable verdicts, empirically showing it outperforms baselines and sets a new benchmark for explainable verification.
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.