辩论未尽之言：基于角色锚定的多智能体推理用于半真半假检测
Debating the Unspoken: Role-Anchored Multi-Agent Reasoning for Half-Truth Detection
AI总结：
提出RADAR框架，通过角色锚定的多智能体辩论（政治家与科学家对抗推理，法官中立裁决）和双阈值早停控制，在噪声检索下有效检测因省略上下文而误导的半真半假陈述。
摘要：
半真半假，即事实正确但因省略上下文而具有误导性的主张，对于专注于显式虚假的事实核查系统而言仍然是一个盲点。解决这种基于省略的操纵需要不仅推理所说内容，还要推理未说内容。我们提出RADAR，一个角色锚定的多智能体辩论框架，用于在现实噪声检索下进行省略感知的事实核查。RADAR为政治家和科学家分配互补角色，他们在共享检索证据上进行对抗性推理，并由中立法官主持。双阈值早停控制器自适应地决定何时达到足够推理以做出裁决。实验表明，RADAR在数据集和骨干网络上始终优于强单智能体和多智能体基线，提高了遗漏检测准确性，同时降低了推理成本。这些结果表明，具有自适应控制的角色锚定、基于检索的辩论是揭示事实核查中缺失上下文的有效且可扩展的框架。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
