ART: Adaptive Reasoning Trees for explainable claim verification
A hierarchical method for claim verification in Large Language Models.
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 \textit{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. We empirically validate ART on multiple datasets, analyzing different argument generators and comparison strategies. Our findings show that ART's structured reasoning significantly outperforms strong baselines like direct and Chain-of-Thought (CoT) methods, establishing a new benchmark for explainable claim verification.
Latest publications
DF-RAG: Enhancing RAG for question answering by balancing relevance and diversity of retrieved chunks
A pipeline that dynamically adapts the level of diversity for each query at test time without requiring prior information.
EACLDeconstructing instruction-following: A new benchmark for granular analysis of Large Language Model instruction compliance abilities
A modular framework that uses a dynamically generated dataset to evaluate the capability of Large Language Models.
EACLGRAVITY: A framework for personalized text generation via profile-grounded synthetic preferences
A framework for generating synthetic, preference data that captures users' interests, values, beliefs, and personality traits.
EACL