Debating the Unspoken: Role-Anchored Multi-Agent Reasoning for Half-Truth Detection
For fact verification systems, RADAR addresses the blind spot of omission-based manipulation by reasoning about unspoken context, offering a scalable and effective framework.
RADAR introduces a role-anchored multi-agent debate framework for detecting half-truths—claims that are factually correct but misleading due to omitted context. It outperforms strong baselines across datasets, improving omission detection accuracy while reducing reasoning cost.
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.