Preprint · 2025 · Open access

Automated Privacy Information Annotation in Large Language Model Interactions

Hang Zeng, Xiangyu Liu, Yongxiang Hu, Chaoyue Niu, Fan Wu, Shaojie Tang, Guihai Chen

arXiv (Cornell University) · Published 27 May 2025 · DOI 10.48550/arxiv.2505.20910

Open PDFView at the publisherCite this paper

In brief

“Automated Privacy Information Annotation in Large Language Model Interactions” is a 2025 preprint by Hang Zeng and 6 co-authors, published in arXiv (Cornell University). OpenAlex counts 8 citations as of 19 November 2026. It is open access under a CC BY-NC-SA licence: the full text is free to read at arXiv (Cornell University).

Citations
8
Most cited in
2026 (5)
References
43
Authors
7

Abstract

Users interacting with large language models (LLMs) under their real identifiers often unknowingly risk disclosing private information. Automatically notifying users whether their queries leak privacy and which phrases leak what private information has therefore become a practical need. Existing privacy detection methods, however, were designed for different objectives and application domains, typically tagging personally identifiable information (PII) in anonymous content, which is insufficient in real-name interaction scenarios with LLMs. In this work, to support the development and evaluation of privacy detection models for LLM interactions that are deployable on local user devices, we construct a large-scale multilingual dataset with 249K user queries and 154K annotated privacy phrases. In particular, we build an automated privacy annotation pipeline with strong LLMs to automatically extract privacy phrases from dialogue datasets and annotate leaked information. We also design evaluation metrics at the levels of privacy leakage, extracted privacy phrase, and privacy information. We further establish baseline methods using light-weight LLMs with both tuning-free and tuning-based methods, and report a comprehensive evaluation of their performance. Evaluation results reveal a gap between current performance and the requirements of real-world LLM applications, motivating future research into more effective local privacy detection methods grounded in our dataset.

Cite this paper

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

APA 7

Zeng, H., Liu, X., Hu, Y., Niu, C., Wu, F., Tang, S., & Chen, G. (2025). Automated Privacy Information Annotation in Large Language Model Interactions. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2505.20910

MLA 9

Zeng, Hang, et al. “Automated Privacy Information Annotation in Large Language Model Interactions.” arXiv (Cornell University), 2025. https://doi.org/10.48550/arxiv.2505.20910.

Chicago

Zeng, Hang, Xiangyu Liu, Yongxiang Hu, Chaoyue Niu, Fan Wu, Shaojie Tang, and Guihai Chen. 2025. “Automated Privacy Information Annotation in Large Language Model Interactions.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2505.20910.

Harvard

Zeng, H. et al. (2025) ‘Automated Privacy Information Annotation in Large Language Model Interactions’, arXiv (Cornell University). doi:10.48550/arxiv.2505.20910.

IEEE

H. Zeng et al., “Automated Privacy Information Annotation in Large Language Model Interactions,” arXiv (Cornell University), 2025, doi: 10.48550/arxiv.2505.20910.

BibTeX

@misc{zeng2025automated,
  title     = {{Automated Privacy Information Annotation in Large Language Model Interactions}},
  author    = {Zeng, Hang and Liu, Xiangyu and Hu, Yongxiang and Niu, Chaoyue and Wu, Fan and Tang, Shaojie and Chen, Guihai},
  howpublished = {arXiv (Cornell University)},
  year      = {2025},
  doi       = {10.48550/arxiv.2505.20910},
  url       = {https://doi.org/10.48550/arxiv.2505.20910}
}

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

Topic and keywords

Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data

  • privacy leakage detection
  • large language models
  • multilingual dataset
  • lightweight LLMs
  • user queries

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Zeng, H., Liu, X., Hu, Y., Niu, C., Wu, F., Tang, S., & Chen, G. (2025). Automated Privacy Information Annotation in Large Language Model Interactions. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2505.20910

How many times has this paper been cited?

8 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?

Hang Zeng, Xiangyu Liu, Yongxiang Hu, Chaoyue Niu, Fan Wu, Shaojie Tang, Guihai Chen.

What is the DOI of this paper?

10.48550/arxiv.2505.20910, permanently at https://doi.org/10.48550/arxiv.2505.20910. 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.