CyberIntel ⬡ News
★ Saved ◆ Cyber Reads
← Back ◬ AI & Machine Learning Apr 23, 2026

Can LLMs Infer Conversational Agent Users' Personality Traits from Chat History?

arXiv Security Archived Apr 23, 2026 ✓ Full text saved

arXiv:2604.19785v1 Announce Type: cross Abstract: 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

Full text archived locally
✦ AI Summary · Claude Sonnet


    Computer Science > Computation and Language [Submitted on 31 Mar 2026] Can LLMs Infer Conversational Agent Users' Personality Traits from Chat History? Derya Cögendez, Verena Zimmermann, Noé Zufferey 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. Subjects: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Cryptography and Security (cs.CR); Computers and Society (cs.CY) Cite as: arXiv:2604.19785 [cs.CL]   (or arXiv:2604.19785v1 [cs.CL] for this version)   https://doi.org/10.48550/arXiv.2604.19785 Focus to learn more Submission history From: Verena Zimmermann [view email] [v1] Tue, 31 Mar 2026 07:29:32 UTC (108 KB) Access Paper: HTML (experimental) view license Current browse context: cs.CL < prev   |   next > new | recent | 2026-04 Change to browse by: cs cs.AI cs.CR cs.CY References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)
    💬 Team Notes
    Article Info
    Source
    arXiv Security
    Category
    ◬ AI & Machine Learning
    Published
    Apr 23, 2026
    Archived
    Apr 23, 2026
    Full Text
    ✓ Saved locally
    Open Original ↗