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

arXiv:2604.19005v1 Announce Type: new 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.

Related

• Co-FactChecker: A Framework for Human-AI Collaborative Claim Verification Using Large Reasoning Models
• A Multi-Agent Approach for Claim Verification from Tabular Data Documents
• Hear Both Sides: Efficient Multi-Agent Debate via Diversity-Aware Message Retention
• Reasoning Graphs: Deterministic Agent Accuracy through Evidence-Centric Chain-of-Thought Feedback
• Answer Only as Precisely as Justified: Calibrated Claim-Level Specificity Control for Agentic Systems

Source: arXiv cs.CL | 2026-04-22