ART：可解释性声明验证的自适应推理树
ART: Adaptive Reasoning Trees for Explainable Claim Verification
AI总结：
ART通过自适应推理树提升声明验证的可解释性和可靠性，通过分层论证结构和法官LLM裁决实现透明且可挑战的决策。
摘要：
大型语言模型（LLMs）是复杂决策的强大候选者，利用庞大的编码知识和卓越的零样本能力。然而，它们在高风险环境中的应用受到其不透明性的阻碍；它们的输出缺乏忠实的解释，无法有效挑战以纠正错误，从而削弱了可信度。在本文中，我们提出了ART（自适应推理树），一种用于声明验证的分层方法。该过程始于一个根声明，然后分支为支持和攻击的子论证。一个论证的强度是通过其子论证的配对锦标赛自下而上确定的，由一个法官LLM裁决，允许系统地得出最终、透明且可挑战的裁决，这在链式思维（CoT）等方法中是缺失的。我们通过多个数据集实证验证ART，分析不同的论证生成器和比较策略。我们的发现表明，ART的结构化推理优于强大的基线，建立了可解释性声明验证的新基准，该基准更可靠，并确保整体决策步骤的清晰性。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
