Preprint · 2024 · Open access

Privacy Leakage Overshadowed by Views of AI: A Study on Human Oversight of Privacy in Language Model Agent

Zhiping Zhang, Guo, Bingcan, Tianshi Li

arXiv (Cornell University) · Published 2 November 2024 · DOI 10.48550/arxiv.2411.01344

Open PDFView at the publisherCite this paper

In brief

“Privacy Leakage Overshadowed by Views of AI: A Study on Human Oversight of Privacy in Language Model Agent” is a 2024 preprint by Zhiping Zhang and 2 co-authors, published in arXiv (Cornell University). OpenAlex counts 30 citations as of 19 November 2026. It is open access under a CC BY licence: the full text is free to read at arXiv (Cornell University).

Citations
30
Most cited in
2025 (21)
References
62
Authors
3

Abstract

Language model (LM) agents that act on users' behalf for personal tasks (e.g., replying emails) can boost productivity, but are also susceptible to unintended privacy leakage risks. We present the first study on people's capacity to oversee the privacy implications of the LM agents. By conducting a task-based survey ($N=300$), we investigate how people react to and assess the response generated by LM agents for asynchronous interpersonal communication tasks, compared with a response they wrote. We found that people may favor the agent response with more privacy leakage over the response they drafted or consider both good, leading to an increased harmful disclosure from 15.7% to 55.0%. We further identified six privacy behavior patterns reflecting varying concerns, trust levels, and privacy preferences underlying people's oversight of LM agents' actions. Our findings shed light on designing agentic systems that enable privacy-preserving interactions and achieve bidirectional alignment on privacy preferences to help users calibrate trust.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Zhang, Z., Bingcan, G., & Li, T. (2024). Privacy Leakage Overshadowed by Views of AI: A Study on Human Oversight of Privacy in Language Model Agent. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2411.01344

MLA 9

Zhang, Zhiping, et al. “Privacy Leakage Overshadowed by Views of AI: A Study on Human Oversight of Privacy in Language Model Agent.” arXiv (Cornell University), 2024. https://doi.org/10.48550/arxiv.2411.01344.

Chicago

Zhang, Zhiping, Guo, Bingcan, and Tianshi Li. 2024. “Privacy Leakage Overshadowed by Views of AI: A Study on Human Oversight of Privacy in Language Model Agent.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2411.01344.

Harvard

Zhang, Z., Bingcan, G. and Li, T. (2024) ‘Privacy Leakage Overshadowed by Views of AI: A Study on Human Oversight of Privacy in Language Model Agent’, arXiv (Cornell University). doi:10.48550/arxiv.2411.01344.

IEEE

Z. Zhang, G. Bingcan, and T. Li, “Privacy Leakage Overshadowed by Views of AI: A Study on Human Oversight of Privacy in Language Model Agent,” arXiv (Cornell University), 2024, doi: 10.48550/arxiv.2411.01344.

BibTeX

@misc{zhang2024privacy,
  title     = {{Privacy Leakage Overshadowed by Views of AI: A Study on Human Oversight of Privacy in Language Model Agent}},
  author    = {Zhang, Zhiping and Bingcan, Guo, and Li, Tianshi},
  howpublished = {arXiv (Cornell University)},
  year      = {2024},
  doi       = {10.48550/arxiv.2411.01344},
  url       = {https://doi.org/10.48550/arxiv.2411.01344}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Social Sciences › Social Sciences › Sociology and Political Science › Privacy, Security, and Data Protection

  • language model agents
  • privacy leakage
  • human oversight
  • privacy preferences
  • trust in AI

Work with this paper

Most-cited papers in Social Sciences

All highly cited Social Sciences papers

Questions about this paper

How do I cite this paper in APA style?

Zhang, Z., Bingcan, G., & Li, T. (2024). Privacy Leakage Overshadowed by Views of AI: A Study on Human Oversight of Privacy in Language Model Agent. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2411.01344

How many times has this paper been cited?

30 times, according to OpenAlex on 19 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at arXiv (Cornell University): sign in and open the PDF from this page.

Who wrote this paper?

Zhiping Zhang, Guo, Bingcan, Tianshi Li.

What is the DOI of this paper?

10.48550/arxiv.2411.01344, permanently at https://doi.org/10.48550/arxiv.2411.01344. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 19 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.