算法自画像:解构ChatGPT中的记忆
The Algorithmic Self-Portrait: Deconstructing Memory in ChatGPT
AI总结:
研究揭示ChatGPT记忆创建中的数据敏感性问题,并提出归因盾框架以保护隐私
摘要:
为了实现个性化和上下文感知的交互,对话AI系统引入了一种新机制:记忆。记忆创造了一种我们称之为算法自画像的新形式个性化,源自用户在私人对话中披露的信息。虽然记忆能够实现更连贯的交流,但记忆创建的底层过程仍然不透明,引发了关于数据敏感性、用户自主性和最终画像准确性的关键问题。为了填补这一研究空白,我们分析了2050个来自80名真实世界ChatGPT用户的记忆条目。我们的分析揭示了三个关键发现:(1)我们数据集中96%的记忆是由对话系统单方面创建的,这可能将自主权转移给用户;(2)在我们的数据集中,记忆包含丰富的GDPR定义的个人数据(在28%的记忆中)以及关于参与者的心理洞察(在52%的记忆中);(3)大量记忆(84%)直接基于用户上下文,表明对话的忠实再现。最后,我们介绍了一个框架——归因盾——它能够预见这些推断,提醒可能敏感的记忆推断,并建议查询改写以保护个人信息而不牺牲实用性。
英文摘要:
To enable personalized and context-aware interactions, conversational AI systems have introduced a new mechanism: Memory. Memory creates what we refer to as the Algorithmic Self-portrait - a new form of personalization derived from users' self-disclosed information divulged within private conversations. While memory enables more coherent exchanges, the underlying processes of memory creation remain opaque, raising critical questions about data sensitivity, user agency, and the fidelity of the resulting portrait. To bridge this research gap, we analyze 2,050 memory entries from 80 real-world ChatGPT users. Our analyses reveal three key findings: (1) A striking 96% of memories in our dataset are created unilaterally by the conversational system, potentially shifting agency away from the user; (2) Memories, in our dataset, contain a rich mix of GDPR-defined personal data (in 28% memories) along with psychological insights about participants (in 52% memories); and (3)~A significant majority of the memories (84%) are directly grounded in user context, indicating faithful representation of the conversations. Finally, we introduce a framework-Attribution Shield-that anticipates these inferences, alerts about potentially sensitive memory inferences, and suggests query reformulations to protect personal information without sacrificing utility.
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。