通过角色对抗辩论发现被省略的上下文，提升事实核查中半真半假的识别能力。
Debating the Unspoken: Role-Anchored Multi-Agent Reasoning for Half-Truth Detection
- 让政治家与科学家基于检索证据进行对抗推理，揭示隐藏信息。
- 在多个数据集上准确率超越基线模型，且推理成本更低。
- 适合关注虚假宣传、信息误导的AI安全与可信内容研究者。
半真半假（half-truths）是那些虽然事实正确但因缺失上下文而具有误导性的陈述，现有事实核查系统多聚焦于显性谎言，对这类隐性操纵仍缺乏应对能力。解决此类问题需要不仅分析已说出的内容，还需推断被省略的信息。我们提出RADAR——一种基于角色锚定的多智能体辩论框架，用于在真实、噪声环境下的遗漏感知事实核查。RADAR为政治家与科学家分配互补角色，二者基于共享检索到的证据进行对抗推理，并由中立裁判监督。采用双阈值早期终止控制器，动态判断是否已达到足够推理深度以做出判决。实验表明，RADAR在多种数据集和模型架构下均显著优于单智能体与多智能体基线模型，提升了遗漏检测准确率的同时降低了推理开销。结果证明，带有自适应控制的角色锚定、检索驱动的辩论机制，是一种高效且可扩展的发掘缺失上下文的有效框架。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。