Coordinating Search-Informed Reasoning and Reasoning-Guided Search in Claim Verification

TL;DR

This paper introduces HARIS, a hierarchical framework that coordinates reasoning and search in multi-hop claim verification, significantly improving accuracy and interpretability by modeling the interleaved process of reasoning and information retrieval.

Contribution

The paper proposes HARIS, a novel hierarchical model that explicitly coordinates reasoning and search, trained with reinforcement learning, to enhance multi-hop claim verification.

Findings

HARIS outperforms existing methods on EX-FEVER and HOVER benchmarks.

The hierarchical approach improves verification accuracy and interpretability.

Reinforcement learning effectively trains the coordinated reasoning and search process.

Abstract

Multi-hop claim verification is inherently challenging, requiring multi-step reasoning to construct verification chains while iteratively searching for information to uncover hidden bridging facts. This process is fundamentally interleaved, as effective reasoning relies on dynamically retrieved evidence, while effective search demands reasoning to refine queries based on partial information. To achieve this, we propose Hierarchical Agent Reasoning and Information Search (HARIS), explicitly modeling the coordinated process of reasoning-driven searching and search-informed reasoning. HARIS consists of a high-level reasoning agent that focuses on constructing the main verification chain, generating factual questions when more information is needed, and a low-level search agent that iteratively retrieves more information, refining its search based on intermediate findings. This design allows each agent to specialize in its respective task, enhancing verification accuracy and interpretability. HARIS is trained using reinforcement learning with outcome-based rewards. Experimental results on the EX-FEVER and HOVER benchmarks demonstrate that HARIS achieves strong performance, greatly advancing multi-hop claim verification.