发表机构
Department of Computer Science, University of Southern California; Department of Computer Science, University of Maryland; Information Sciences Institute, University of Southern California; School of Computer Science, University of Sydney（计算机科学系，南加州大学; 计算机科学系，马里兰大学; 信息科学研究所，南加州大学; 计算机科学学院，悉尼大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究人工智能辅助信息评估中修辞模式，通过主体内研究考察八种修辞模式，发现支架式解释与最高准确率提升相关，对抗条件也能适度提高准确率，还探讨了设计不同修辞风格对话代理的意义及相关权衡。
AI 中文摘要
先前关于人工智能辅助信息评估的工作主要集中在人工智能系统传达的内容上，比较解释类型和格式，其回应主要采用指令性修辞，即系统给出裁决，用户被动接受。虽然辩论式互动最近在促使批判性评估而非顺从方面显示出前景，但构建人工智能回应的修辞模式以及它们如何引发反思、不确定性或独立推理在很大程度上仍未得到研究。为解决此问题，我们研究了八种已知能引发思考的修辞模式：故意误导、解释性替代、支架式解释、引发不信任、信息扭曲、另类框架、苏格拉底式提问以及神谕基线。通过对98名参与者进行的关于按需提示事实核查任务的主体内研究，我们观察到初步证据表明支架式解释与最高的准确率提升相关，并鼓励更深入的反思。令人惊讶的是，对抗条件也适度提高了准确率。参与者最喜欢另类框架，最不喜欢解释性替代，主要是因为后者的时间成本较高。我们讨论了设计具有不同修辞风格的对话代理的意义以及在用户表现、满意度和思考之间的权衡。
英文摘要
Prior work on AI-assisted information evaluation has largely focused on what AI systems communicate, comparing explanation types and formats, with responses predominantly cast in directive rhetoric where the system delivers a verdict and the user passively accepts it. While debate-style interactions have recently shown promise in prompting critical evaluation over deference, the rhetorical patterns that structure AI responses and how they might induce reflection, uncertainty, or independent reasoning remain largely unexamined. To address this, we investigated eight rhetorical patterns known to induce contemplation: Intentional Misleading, Interpretive Alternative, Scaffold Explanation, Triggering Distrust, Information Distortion, Alternative Framing, Socratic Questioning, and an Oracle baseline. Through a within-subject study with n=98 participants on a hint-on-demand fact verification task, we observed preliminary evidence that Scaffold Explanation were associated with the highest accuracy gains, and encouraging deeper reflection. Surprisingly, the adversarial conditions also improved accuracy modestly. Participants preferred Alternative Framing most and Interpretive Alternative least, largely due to the latter's perceived time cost. We discuss the implications of designing conversational agents with varied rhetorical styles and the trade-offs among user performance, satisfaction, and contemplation.
Comments13 pages, 6 figures, 1 table
