Conference paper · 2025

Utility-Preserving DP-SGD for Large Language Models in Mental-Health EHRs

Kuber Jain, Ankur Vora, Chakra Pavan Kumar Kota, Faiz Gouri

IEEE International Conference on Big Data and Artificial Intelligence (BDAI), 117–122 · Published 22 August 2025 · DOI 10.1109/bdai66031.2025.11325541

View at the publisherCite this paper

In brief

“Utility-Preserving DP-SGD for Large Language Models in Mental-Health EHRs” is a 2025 conference paper by Kuber Jain and 3 co-authors, published in IEEE International Conference on Big Data and Artificial Intelligence (BDAI). OpenAlex counts 2 citations as of 19 November 2026, which puts it in the top 6% of works published in 2025 by citations. The publisher's version is not open access, and OpenAlex records no free legal copy.

Citations
2
Most cited in
2026 (2)
Field-weighted impact
0.42
References
15
Authors
4

Abstract

Large language models can ease psychiatrists’ heavy documentation load-but only if they learn from patient notes without revealing anything about the people behind them. We introduce a two-step privacy pipeline. First, a mix of pattern-matching rules and a neural tagger scrubs lingering names, dates, and other identifiers, removing 99% of residual protected-health-information (PHI) from notes… Read the full abstract at the publisher.

Excerpt. This paper is not open access.

Cite this paper

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

APA 7

Jain, K., Vora, A., Kota, C. P. K., & Gouri, F. (2025). Utility-Preserving DP-SGD for Large Language Models in Mental-Health EHRs. IEEE International Conference on Big Data and Artificial Intelligence (BDAI), 117–122. https://doi.org/10.1109/bdai66031.2025.11325541

MLA 9

Jain, Kuber, et al. “Utility-Preserving DP-SGD for Large Language Models in Mental-Health EHRs.” IEEE International Conference on Big Data and Artificial Intelligence (BDAI), 2025, pp. 117–122. https://doi.org/10.1109/bdai66031.2025.11325541.

Chicago

Jain, Kuber, Ankur Vora, Chakra Pavan Kumar Kota, and Faiz Gouri. 2025. “Utility-Preserving DP-SGD for Large Language Models in Mental-Health EHRs.” IEEE International Conference on Big Data and Artificial Intelligence (BDAI): 117–122. https://doi.org/10.1109/bdai66031.2025.11325541.

Harvard

Jain, K. et al. (2025) ‘Utility-Preserving DP-SGD for Large Language Models in Mental-Health EHRs’, IEEE International Conference on Big Data and Artificial Intelligence (BDAI), pp. 117–122. doi:10.1109/bdai66031.2025.11325541.

IEEE

K. Jain, A. Vora, C. P. K. Kota, and F. Gouri, “Utility-Preserving DP-SGD for Large Language Models in Mental-Health EHRs,” IEEE International Conference on Big Data and Artificial Intelligence (BDAI), pp. 117–122, 2025, doi: 10.1109/bdai66031.2025.11325541.

BibTeX

@inproceedings{jain2025utility,
  title     = {{Utility-Preserving DP-SGD for Large Language Models in Mental-Health EHRs}},
  author    = {Jain, Kuber and Vora, Ankur and Kota, Chakra Pavan Kumar and Gouri, Faiz},
  booktitle = {IEEE International Conference on Big Data and Artificial Intelligence (BDAI)},
  year      = {2025},
  pages     = {117--122},
  doi       = {10.1109/bdai66031.2025.11325541},
  url       = {https://doi.org/10.1109/bdai66031.2025.11325541}
}

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

  • differential privacy
  • large language models
  • protected health information
  • data de-identification
  • membership inference attacks
  • privacy-preserving fine-tuning
  • MIMIC-IV
  • clinical language models

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?

Jain, K., Vora, A., Kota, C. P. K., & Gouri, F. (2025). Utility-Preserving DP-SGD for Large Language Models in Mental-Health EHRs. IEEE International Conference on Big Data and Artificial Intelligence (BDAI), 117–122. https://doi.org/10.1109/bdai66031.2025.11325541

How many times has this paper been cited?

2 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?

OpenAlex records no free legal copy. Check your library's access, the authors' pages or a repository, or ask the corresponding author for a copy.

Who wrote this paper?

Kuber Jain, Ankur Vora, Chakra Pavan Kumar Kota, Faiz Gouri.

What is the DOI of this paper?

10.1109/bdai66031.2025.11325541, permanently at https://doi.org/10.1109/bdai66031.2025.11325541. 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.