评估生成式AI系统中对话交互的个人信息输出
Evaluating Personal Information Output from Conversational Interactions in Generative AI Systems
查看机构详情
- Kobe City University of Foreign Studies（神户市外国语大学）
- Kobe City College of Technology（神户市立工业高等专门学校）
机构由 AI 辅助整理，请以论文原文为准。
浏览论文内容
中文总结 AI 辅助
本研究通过15名日本参与者评估GPT-5.2系列模型在对话中输出个人信息的倾向，发现事实输出更保守，行为与语言属性准确性高，推断画像可能源于上下文信息，为隐私讨论提供参考。
中文摘要 AI 辅助
这项探索性试点研究评估了使用GPT-5.2 Instant和GPT-5.2 Thinking的生成式AI系统中持续对话交互所输出的个人信息的范围与感知准确性，并将输出分为三类：事实、推断和置信度。基于从15名日本参与者获得的评估结果，模型设计的差异对个人信息输出倾向的影响有限。与推断类型相比，事实类型表现出更为保守的输出模式。在属性类别方面，研究结果表明，与身份识别相关的核心个人属性被相对保守地处理，而行为属性和语言属性在事实和推断输出中均表现出更高的准确性。此外，整体画像、心理与认知以及残余属性更容易被推断出来，即使这些属性没有明确的事实输出支持。值得注意的是，在推断类型中这些属性缺乏空输出，这表明此类推断画像可能是从间接可用的上下文信息中构建的。这些发现可能有助于未来关于生成式AI系统中隐私意识和个人信息推断的讨论。
英文摘要
This exploratory pilot study evaluates the scope and perceived accuracy of personal information output from ongoing conversational interactions in generative AI systems using GPT-5.2 Instant and GPT-5.2 Thinking, categorized into three output types: Fact, Inference, and Confidence. Based on the evaluation results obtained from 15 Japanese participants, differences in model design have limited impact on personal information output tendencies. Compared with the Inference type, the Fact type shows a more conservative output pattern. Regarding attribute categories, the findings indicate that Core Personal attributes associated with identification are treated relatively conservatively, whereas Behavioral and Linguistic attributes show higher accuracy across both Fact and Inference outputs. Furthermore, Holistic Profile, Psychological and Cognitive, and Residual attributes are more readily inferred, even when not supported by explicit factual outputs. Notably, the lack of null outputs for these attributes in the Inference type suggests that such inferred profiles may be constructed from indirectly available contextual information. The findings may contribute to future discussions regarding privacy awareness and personal information inference in generative AI systems.
