Debating the Unspoken: Role-Anchored Multi-Agent Reasoning for Half-Truth Detection

TL;DR

RADAR introduces a role-anchored multi-agent debate framework that enhances half-truth detection by reasoning about omitted context, outperforming existing methods in accuracy and efficiency.

Contribution

It presents a novel debate-based approach with role assignment and adaptive control for omission-aware fact verification in noisy retrieval scenarios.

Findings

RADAR outperforms strong baselines in omission detection accuracy.

The framework reduces reasoning cost through early termination.

Experiments validate the effectiveness of role-anchored debate in uncovering missing context.

Abstract

Half-truths, claims that are factually correct yet misleading due to omitted context, remain a blind spot for fact verification systems focused on explicit falsehoods. Addressing such omission-based manipulation requires reasoning not only about what is said, but also about what is left unsaid. We propose RADAR, a role-anchored multi-agent debate framework for omission-aware fact verification under realistic, noisy retrieval. RADAR assigns complementary roles to a Politician and a Scientist, who reason adversarially over shared retrieved evidence, moderated by a neutral Judge. A dual-threshold early termination controller adaptively decides when sufficient reasoning has been reached to issue a verdict. Experiments show that RADAR consistently outperforms strong single- and multi-agent baselines across datasets and backbones, improving omission detection accuracy while reducing reasoning cost. These results demonstrate that role-anchored, retrieval-grounded debate with adaptive control is an effective and scalable framework for uncovering missing context in fact verification. The code is available at https://github.com/tangyixuan/RADAR.