Conference paper · 2026 · Open access
Clinically Grounded Privacy Evaluation of Medical LMs
Conference on Empirical Methods in Natural Language Processing (EMNLP), 54266–54295 · Published 1 January 2026 · DOI 10.18653/2026.emnlp-main.2388
In brief
“Clinically Grounded Privacy Evaluation of Medical LMs” is a 2026 conference paper by Sasha Ronaghi and 8 co-authors, published in Conference on Empirical Methods in Natural Language Processing (EMNLP). OpenAlex counts 1 citations as of 19 November 2026. It is open access: the full text is free to read at Conference on Empirical Methods in Natural Language Processing (EMNLP).
- Citations
- 1
- Most cited in
- 2026 (1)
- Field-weighted impact
- 0.88
- References
- 51
- Authors
- 9
Abstract
Medical language models (LMs) can memorize and reproduce protected health information, but privacy evaluations often focus on recovery of training text rather than disclosure under realistic threat models.We introduce a clinically grounded framework that evaluates leakage along a graded axis of adversarial access, ranging from publicly inferable demographics to leaked note fragments.At each tier, we measure verbatim memorization of patientspecific text and semantic leakage of sensitive diagnoses.Applying the framework to an LM continually pretrained on 378k clinical notes, we find that routine encounter metadata (i.e., name, date of birth, visit date, provider name, and practice location) elicits high rates of verbatim memorization across a patient's timeline and sensitive-diagnosis recovery (AUROC 0.91 for abortion, 0.82 for HIV).At the same time, exact-match memorization can overstate disclosure: 36% of memorized tokens reflect templated documentation.Our work highlights the risks of training on longitudinal clinical data and provides a practical, reusable framework for contextual privacy evaluation of medical LMs.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Ronaghi, S., Tonekaboni, S., Stempfle, L., Utti, V., Cahoon, J. L., Hendrix, N., Vala, A., Ghassemi, M., & Alsentzer, E. (2026). Clinically Grounded Privacy Evaluation of Medical LMs. Conference on Empirical Methods in Natural Language Processing (EMNLP), 54266–54295. https://doi.org/10.18653/2026.emnlp-main.2388
MLA 9
Ronaghi, Sasha, et al. “Clinically Grounded Privacy Evaluation of Medical LMs.” Conference on Empirical Methods in Natural Language Processing (EMNLP), 2026, pp. 54266–54295. https://doi.org/10.18653/2026.emnlp-main.2388.
Chicago
Ronaghi, Sasha, Sana Tonekaboni, Lena Stempfle, Vivian Utti, Jordan Li Cahoon, Nathaniel Hendrix, Ayin Vala, Marzyeh Ghassemi, and Emily Alsentzer. 2026. “Clinically Grounded Privacy Evaluation of Medical LMs.” Conference on Empirical Methods in Natural Language Processing (EMNLP): 54266–54295. https://doi.org/10.18653/2026.emnlp-main.2388.
Harvard
Ronaghi, S. et al. (2026) ‘Clinically Grounded Privacy Evaluation of Medical LMs’, Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 54266–54295. doi:10.18653/2026.emnlp-main.2388.
IEEE
S. Ronaghi et al., “Clinically Grounded Privacy Evaluation of Medical LMs,” Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 54266–54295, 2026, doi: 10.18653/2026.emnlp-main.2388.
BibTeX
@inproceedings{ronaghi2026clinically,
title = {{Clinically Grounded Privacy Evaluation of Medical LMs}},
author = {Ronaghi, Sasha and Tonekaboni, Sana and Stempfle, Lena and Utti, Vivian and Cahoon, Jordan Li and Hendrix, Nathaniel and Vala, Ayin and Ghassemi, Marzyeh and Alsentzer, Emily},
booktitle = {Conference on Empirical Methods in Natural Language Processing (EMNLP)},
year = {2026},
pages = {54266--54295},
doi = {10.18653/2026.emnlp-main.2388},
url = {https://doi.org/10.18653/2026.emnlp-main.2388}
}
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
- clinical language models
- privacy analysis
- protected health information
- demographic inference
- clinical notes
- disclosure risk
Work with this paper
Most-cited papers in Computer Science
- ImageNet classification with deep convolutional neural networksAlex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton · Communications of the ACM · 2017 · 114,726 citations
- Long Short-Term MemorySepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 109,097 citations
- A Mathematical Theory of CommunicationClaude E. Shannon · Bell System Technical Journal · 1948 · 91,736 citations
- Deep learningYann LeCun, Yoshua Bengio, Geoffrey E. Hinton · Nature · 2015 · 90,226 citations
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksShaoqing Ren, Kaiming He, Ross Girshick and 1 more · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2016 · 74,143 citations
Questions about this paper
How do I cite this paper in APA style?
Ronaghi, S., Tonekaboni, S., Stempfle, L., Utti, V., Cahoon, J. L., Hendrix, N., Vala, A., Ghassemi, M., & Alsentzer, E. (2026). Clinically Grounded Privacy Evaluation of Medical LMs. Conference on Empirical Methods in Natural Language Processing (EMNLP), 54266–54295. https://doi.org/10.18653/2026.emnlp-main.2388
How many times has this paper been cited?
1 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 Conference on Empirical Methods in Natural Language Processing (EMNLP): sign in and open the PDF from this page.
Who wrote this paper?
Sasha Ronaghi, Sana Tonekaboni, Lena Stempfle, Vivian Utti, Jordan Li Cahoon, Nathaniel Hendrix, Ayin Vala, Marzyeh Ghassemi, Emily Alsentzer.
What is the DOI of this paper?
10.18653/2026.emnlp-main.2388, permanently at https://doi.org/10.18653/2026.emnlp-main.2388. 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.