发表机构
The University of Tokyo; Institute of Industrial Science, The University of Tokyo; Korea Advanced Institute of Science and Technology; Georgia Institute of Technology; Sony CSL Kyoto（东京大学; 东京大学工业科学研究所; 韩国科学技术院; 佐治亚理工学院; 索尼京都计算机科学实验室）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究针对生成式AI带来的“流畅陷阱”问题，提出Provenance Density界面可视化文本中已验证主张的密度，经用户研究和技术审计证实其能提升内容辨别能力，为AI内容透明度提供新方向。
AI 中文摘要
随着生成式AI让产出流畅的文本变得成本低廉，用户不再能依赖流畅度作为真实性的替代指标。我们将这种失效模式称为“流畅陷阱”：用户既会相信流畅的虚构内容，又会在内容被披露为AI生成后贬低准确信息。二元的“Made with AI”标签仅回应了作者身份披露，却未展示支撑主张的依据。我们提出Provenance Density（来源密度），这是一种可视化证据的界面，可展示文本中已验证主张的密度。在有81名参与者的用户研究中，理想化的Provenance Density界面使参与者在真实内容与虚构内容之间产生了显著的辨别差距（+4.15分，d=1.82），而未获得任何信号的参与者未表现出可检测的辨别能力。对200个样本的技术审计显示，仅检索密度不足以实现辨别；出乎意料的是，Consistency Veto（一致性否决）在动态查询中承载了大部分辨别信号。随着AI生成内容与人类写作难以区分，有效的透明度必须从作者身份披露转向证据可视化。
英文摘要
As generative AI makes polished prose cheap to produce, users can no longer rely on fluency as a proxy for truth. We call this failure mode the Fluency Trap: users trust fluent hallucinations while also discounting accurate content once it is disclosed as AI-generated. Binary ``Made with AI'' labels respond with authorship disclosure, but they do not show what supports a claim. We propose Provenance Density, an evidence-visualization interface that shows the density of verified claims in a text. In a user study with 81 participants, an idealized Provenance Density interface produced a large discernment gap between truth and fabrication ($+4.15$ points, $d=1.82$), whereas participants given no signal showed no detectable discrimination. A technical audit with 200 samples shows that retrieval density alone is insufficient; unexpectedly, the Consistency Veto carries most of the discriminative signal on dynamic queries. As AI-generated content becomes indistinguishable from human writing, effective transparency must move from authorship disclosure toward evidence visualization.
