大语言模型能否从聊天记录中推断出对话代理用户的人格特质？
Can LLMs Infer Conversational Agent Users' Personality Traits from Chat History?
AI总结：
研究探讨了大语言模型能否从用户与对话代理的交互中推断出人格特质，通过分析ChatGPT日志数据，发现模型在多个案例中能以高于随机水平的准确率推断出性格特质，揭示了与对话代理交互带来的隐私风险。
摘要：
敏感信息，如个人性格知识，可能被滥用以影响行为（例如通过个性化消息）。为评估个体的性格是否能从用户与基于大语言模型（LLM）的对话代理（CAs）的交互中推断出来，我们分析并量化使用CAs相关的隐私风险。我们收集了N=668名参与者的实际ChatGPT日志，包含62,090条个体聊天记录，并报告了共享数据类型和使用案例的统计数据。我们对RoBERTa-base文本分类模型进行了微调，以从CAs交互中推断性格特质。研究发现，这些模型在多个案例中能够以高于随机水平的准确率（三元分类）推断出性格特质。例如，在关系和个人反思的交互中，外向性准确率比基线提高了+44%。本研究揭示了与CAs交互所带来的隐私风险，并提供了关于不同类型的交互所关联的风险水平的细粒度见解。
英文摘要：
Sensitive information, such as knowledge about an individual's personality, can be can be misused to influence behavior (e.g., via personalized messaging). To assess to what extent an individual's personality can be inferred from user interactions with LLM-based conversational agents (CAs), we analyze and quantify related privacy risks of using CAs. We collected actual ChatGPT logs from N=668 participants, containing 62,090 individual chats, and report statistics about the different types of shared data and use cases. We fine-tuned RoBERTa-base text classification models to infer personality traits from CA interactions. The findings show that these models achieve trait inference with accuracy (ternary classification) better than random in multiple cases. For example, for extraversion, accuracy improves by +44% relative to the baseline on interactions for relationships and personal reflection. This research highlights how interactions with CAs pose privacy risks and provides fine-grained insights into the level of risk associated with different types of interactions.
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。
