---
title: "Multi-Token Completion for Text Anonymization — Madaan 2026"
description: "This paper addresses a less studied question: what should replace the redacted spans? 50 references, cited by 1 paper here."
authors: ["Pulkit Madaan", "Krithika Ramesh", "Lisa Bauer", "Charith Peris", "Anjalie Field"]
year: 2026
venue: "Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)"
source: "https://aclanthology.org/2026.eacl-long.276/"
doi: "10.18653/v1/2026.eacl-long.276"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/madaan-2026-multi-token-completion-text-anonymization/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/madaan-2026-multi-token-completion-text-anonymization/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/15/) / Multi-Token Completion for Text Anonymization

# Multi-Token Completion for Text Anonymization

**Authors:** Pulkit Madaan, [Krithika Ramesh](https://md.research.elamur.ai/free/en/authors/krithika-ramesh/), [Lisa Bauer](https://md.research.elamur.ai/free/en/authors/lisa-bauer/), [Charith Peris](https://md.research.elamur.ai/free/en/authors/charith-peris/) and [Anjalie Field](https://md.research.elamur.ai/free/en/authors/anjalie-field/) · **Year:** 2026 · **Venue:** [Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)](https://md.research.elamur.ai/free/en/venues/eacl/) ([EACL 2026](https://md.research.elamur.ai/free/en/venues/eacl/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.eacl-long.276/) · [PDF](https://aclanthology.org/2026.eacl-long.276.pdf) · [DOI 10.18653/v1/2026.eacl-long.276](https://doi.org/10.18653/v1/2026.eacl-long.276) · [OpenAlex](https://openalex.org/W7140078172)

**Citations:** 0 citations (OpenAlex, 2026-10-14) · [1](https://md.research.elamur.ai/free/en/papers/madaan-2026-multi-token-completion-text-anonymization/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
Most anonymization research focuses on finding and removing sensitive content. This paper addresses a less studied question: what should replace the redacted spans? Realistic surrogates can make leaked real identifiers harder to spot, following the Hiding In Plain Sight idea, and they keep text usable even under heavy redaction. The authors define surrogate prediction as a task with evaluation criteria tied to practical use. They build a two-stage pipeline: a Longformer detector trained on TAB marks direct and quasi-identifiers, then a masked language model fills the gaps. Ordinary MLMs predict only one subword per mask, so the authors extend the decoder vocabulary with multi-token phrases (MTC). Their variant, SS-MTC, takes those phrases from spans that the detector flags in Wikipedia. Human and automatic evaluations show more plausible output and better downstream utility than naive masking, differential privacy, and LLM-based alternatives. The method also transfers to clinical notes without retraining. Because it needs little compute, data holders could anonymize data locally before sharing it.

## Key points
- **Main data:** the Text Anonymization Benchmark (TAB), with 1,268 English European Court of Human Rights cases split 1014/127/127. Quasi-identifiers make up 93.47% of the annotated sensitive spans.
- **Models:** both the detector and the infiller use `longformer-base-4096`, which fits 93.3% of the documents in one pass. On the TAB test set, the detector reaches recall of 0.929 (token) and 0.905 (mention), and precision of 0.882 (token) and 0.743 (mention).
- **Efficiency:** MTC/SS-MTC fine-tune only the output embedding matrix. Building SS-MTC takes a few hours on a single T4 GPU, and API-based LLMs are deliberately avoided.
- **Baselines:** two simple multi-mask schemes, Naive Static-3 (three masks per span) and Naive Adaptive (one mask per original token), plus differential-privacy and LLM-based approaches.
- **Downstream and cross-domain tests:** utility was measured with LexAbSumm summarization and with coreference resolution, where the gains were larger. Generalization was tested on i2b2/VA clinical notes.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

## Institutions

- [Johns Hopkins University](https://md.research.elamur.ai/free/en/universities/johns-hopkins-university/) — University, Baltimore, United States · 240 works · 96,487 citations

📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 16,039 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 15,891 works

## Cite

Cite as: Pulkit Madaan, Krithika Ramesh, Lisa Bauer, Charith Peris and Anjalie Field. 2026. Multi-Token Completion for Text Anonymization. Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers).

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{madaan2026multi,
  title = {{Multi-Token Completion for Text Anonymization}},
  author = {Pulkit Madaan, Krithika Ramesh, Lisa Bauer, Charith Peris and Anjalie Field},
  booktitle = {Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2026},
  doi = {10.18653/v1/2026.eacl-long.276},
  url = {https://doi.org/10.18653/v1/2026.eacl-long.276}
}
```

- [← previous Multi-Modal-Minds@CHiPSAL 2026: A Comparative Study of Textual, Visual and Multimodal Architecture for Nepali Meme Moderation](https://md.research.elamur.ai/free/en/papers/shrestha-2026-multi-modal-minds-chipsal-2026/)
- [next → Multilingual Communication in the Asylum Context: Evaluating LLM-Based Machine Translation with Fuzzy Match Augmentation and Adaptive NMT across Resource Conditions under Low-Data Constraints](https://md.research.elamur.ai/free/en/papers/moerman-2026-multilingual-communication-asylum-context-evaluating/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/15/)

## References

50 references, 10 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Allison Adams, Eric Aili, Daniel Aioanei, Rebecca Jonsson, Lina Mickelsson, Dagmar Mikmekova, Fred Roberts, Javier Fernandez Valencia, and Roger Wechsler. 2019. AnonyMate: A toolkit for anonymizing unstructured chat data. In Proceedings of the Workshop on NLP and Pseudonymisation, pages 1–7, Turku,… [find](https://scholar.google.com/scholar?q=Allison+Adams%2C+Eric+Aili%2C+Daniel+Aioanei%2C+Rebecca+Jonsson%2C+Lina+Mickelsson%2C+Dagmar+Mikmekova%2C+Fred+Roberts%2C+Javier+Fernandez+Valencia%2C+and+Roger+Wechsler%2E+2019%2E+AnonyMate%3A+A+toolkit+for+anonymizing+un)
2. Alyaa Alfalahi, Sara Brissman, and Hercules Dalianis. 2012. Pseudonymisation of personal names and other phis in an annotated clinical swedish corpus. In Third Workshop on Building and Evaluating Resources for Biomedical Text Mining (BioTxtM 2012) Held in Conjunction with LREC, pages 49–54. [find](https://scholar.google.com/scholar?q=Alyaa+Alfalahi%2C+Sara+Brissman%2C+and+Hercules+Dalianis%2E+2012%2E+Pseudonymisation+of+personal+names+and+other+phis+in+an+annotated+clinical+swedish+corpus%2E+In+Third+Workshop+on+Building+and+Evaluating+Reso)
3. Ahmed Musa Awon, Yun Lu, Shera Potka, and Alex Thomo. 2025. CluSanT: Differentially private and semantically coherent text sanitization. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume… [find](https://scholar.google.com/scholar?q=Ahmed+Musa+Awon%2C+Yun+Lu%2C+Shera+Potka%2C+and+Alex+Thomo%2E+2025%2E+CluSanT%3A+Differentially+private+and+semantically+coherent+text+sanitization%2E+In+Proceedings+of+the+2025+Conference+of+the+Nations+of+the+Ame)
4. Iz Beltagy, Matthew E. Peters, and Arman Cohan. 2020. [Longformer: The long-document transformer](https://md.research.elamur.ai/free/en/papers/beltagy-2020-longformer-long-document-transformer/). arXiv:2004.05150.
5. David Carrell, Bradley Malin, John Aberdeen, Samuel Bayer, Cheryl Clark, Ben Wellner, and Lynette Hirschman. 2012. Hiding in plain sight: use of realistic surrogates to reduce exposure of protected health information in clinical text. Journal of the American Medical Informatics Association, 20(2):34… [find](https://scholar.google.com/scholar?q=David+Carrell%2C+Bradley+Malin%2C+John+Aberdeen%2C+Samuel+Bayer%2C+Cheryl+Clark%2C+Ben+Wellner%2C+and+Lynette+Hirschman%2E+2012%2E+Hiding+in+plain+sight%3A+use+of+realistic+surrogates+to+reduce+exposure+of+protected+he)
6. Aipeng Chen, Jitendra Jonnagaddala, Chandini Nekkantti, and Siaw-Teng Liaw. 2019. Generation of surrogates for de-identification of electronic health records. In MEDINFO 2019: Health and Wellbeing e-Networks for All, pages 70–73. IOS Press. [find](https://scholar.google.com/scholar?q=Aipeng+Chen%2C+Jitendra+Jonnagaddala%2C+Chandini+Nekkantti%2C+and+Siaw%2DTeng+Liaw%2E+2019%2E+Generation+of+surrogates+for+de%2Didentification+of+electronic+health+records%2E+In+MEDINFO+2019%3A+Health+and+Wellbeing+e%2DN)
7. Sai Chen, Fengran Mo, Yanhao Wang, Cen Chen, Jian-Yun Nie, Chengyu Wang, and Jamie Cui. 2023. A customized text sanitization mechanism with differential privacy. In Findings of the Association for Computational Linguistics: ACL 2023, pages 5747– 5758, Toronto, Canada. Association for Computational L… [find](https://scholar.google.com/scholar?q=Sai+Chen%2C+Fengran+Mo%2C+Yanhao+Wang%2C+Cen+Chen%2C+Jian%2DYun+Nie%2C+Chengyu+Wang%2C+and+Jamie+Cui%2E+2023%2E+A+customized+text+sanitization+mechanism+with+differential+privacy%2E+In+Findings+of+the+Association+for+Com)
8. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. [BERT: Pre-training of deep bidirectional transformers for language understanding](https://md.research.elamur.ai/free/en/papers/devlin-2019-bert-pre-training-deep-bidirectional/). In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies,…
9. Yao Dou, Isadora Krsek, Tarek Naous, Anubha Kabra, Sauvik Das, Alan Ritter, and Wei Xu. 2024. Reducing privacy risks in online self-disclosures with language models. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 13732– 13754… [find](https://scholar.google.com/scholar?q=Yao+Dou%2C+Isadora+Krsek%2C+Tarek+Naous%2C+Anubha+Kabra%2C+Sauvik+Das%2C+Alan+Ritter%2C+and+Wei+Xu%2E+2024%2E+Reducing+privacy+risks+in+online+self%2Ddisclosures+with+language+models%2E+In+Proceedings+of+the+62nd+Annual+)
10. Elisabeth Eder, Ulrike Krieg-Holz, and Udo Hahn. 2019. De-identification of emails: Pseudonymizing privacy-sensitive data in a German email corpus. In Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2019), pages 259–269, Varna, Bulgaria. INCOMA Lt… [find](https://scholar.google.com/scholar?q=Elisabeth+Eder%2C+Ulrike+Krieg%2DHolz%2C+and+Udo+Hahn%2E+2019%2E+De%2Didentification+of+emails%3A+Pseudonymizing+privacy%2Dsensitive+data+in+a+German+email+corpus%2E+In+Proceedings+of+the+International+Conference+on+Re)
11. Anjalie Field, Amanda Coston, Nupoor Gandhi, Alexandra Chouldechova, Emily Putnam-Hornstein, David Steier, and Yulia Tsvetkov. 2023. Examining risks of racial biases in nlp tools for child protective services. In Proceedings of the 2023 ACM Conference on Fairness, Accountability, and Transparency, F… [find](https://scholar.google.com/scholar?q=Anjalie+Field%2C+Amanda+Coston%2C+Nupoor+Gandhi%2C+Alexandra+Chouldechova%2C+Emily+Putnam%2DHornstein%2C+David+Steier%2C+and+Yulia+Tsvetkov%2E+2023%2E+Examining+risks+of+racial+biases+in+nlp+tools+for+child+protective+)
12. Nupoor Gandhi, Anjalie Field, and Emma Strubell. 2023. [Annotating mentions alone enables efficient domain adaptation for coreference resolution](https://md.research.elamur.ai/free/en/papers/gandhi-2023-annotating-mentions-alone-enables-efficient/). In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 10543–10558, Toronto, Canada. Ass…
13. Ary L. Goldberger, Luis A. N. Amaral, Leon Glass, Jeffrey M. Hausdorff, Plamen Ch. Ivanov, Roger G. Mark, Joseph E. Mietus, George B. Moody, Chung-Kang Peng, and H. Eugene Stanley. 2000. Physiobank, physiotoolkit, and physionet. Circulation, 101(23):e215–e220. [find](https://scholar.google.com/scholar?q=Ary+L%2E+Goldberger%2C+Luis+A%2E+N%2E+Amaral%2C+Leon+Glass%2C+Jeffrey+M%2E+Hausdorff%2C+Plamen+Ch%2E+Ivanov%2C+Roger+G%2E+Mark%2C+Joseph+E%2E+Mietus%2C+George+B%2E+Moody%2C+Chung%2DKang+Peng%2C+and+H%2E+Eugene+Stanley%2E+2000%2E+Physiobank%2C+p)
14. Mandy Guo, Joshua Ainslie, David Uthus, Santiago Ontanon, Jianmo Ni, Yun-Hsuan Sung, and Yinfei Yang. 2022. [LongT5: Efficient text-to-text transformer for long sequences](https://md.research.elamur.ai/free/en/papers/guo-2022-longt5-efficient-text-text-transformer/). In Findings of the Association for Computational Linguistics: NAACL 2022, pages 724– 736, Seattle, United States. Association for…
15. Fadi Hassan, Josep Domingo-Ferrer, and Jordi Soria-Comas. 2018. Anonymization of unstructured data via named-entity recognition. In Modeling Decisions for Artificial Intelligence: 15th International Conference, MDAI 2018, Mallorca, Spain, October 15–18, 2018, Proceedings, page 296–305, Berlin, Heide… [find](https://scholar.google.com/scholar?q=Fadi+Hassan%2C+Josep+Domingo%2DFerrer%2C+and+Jordi+Soria%2DComas%2E+2018%2E+Anonymization+of+unstructured+data+via+named%2Dentity+recognition%2E+In+Modeling+Decisions+for+Artificial+Intelligence%3A+15th+International+C)
16. Lynette Hirschman and John Aberdeen. 2010. Measuring risk and information preservation: Toward new metrics for de-identification of clinical texts. In Proceedings of the NAACL HLT 2010 Second Louhi Workshop on Text and Data Mining of Health Documents, pages 72–75, Los Angeles, California, USA. Assoc… [find](https://scholar.google.com/scholar?q=Lynette+Hirschman+and+John+Aberdeen%2E+2010%2E+Measuring+risk+and+information+preservation%3A+Toward+new+metrics+for+de%2Didentification+of+clinical+texts%2E+In+Proceedings+of+the+NAACL+HLT+2010+Second+Louhi+Wo)
17. Matthew Honnibal, Ines Montani, Sofie Van Lan-deghem, and Adriane Boyd. 2020. spaCy: Industrial-strength Natural Language Processing in Python. [find](https://scholar.google.com/scholar?q=Matthew+Honnibal%2C+Ines+Montani%2C+Sofie+Van+Lan%2Ddeghem%2C+and+Adriane+Boyd%2E+2020%2E+spaCy%3A+Industrial%2Dstrength+Natural+Language+Processing+in+Python%2E)
18. Zilyu Ji, Yuntian Shen, Jionghao Lin, and Kenneth R. Koedinger. 2025. Enhancing the de-identification of personally identifiable information in educational data. Journal of Educational Data Mining, 17(2):55–85. [find](https://scholar.google.com/scholar?q=Zilyu+Ji%2C+Yuntian+Shen%2C+Jionghao+Lin%2C+and+Kenneth+R%2E+Koedinger%2E+2025%2E+Enhancing+the+de%2Didentification+of+personally+identifiable+information+in+educational+data%2E+Journal+of+Educational+Data+Mining%2C+17)
19. Alistair EW Johnson, Tom J Pollard, Lu Shen, Li-wei H Lehman, Mengling Feng, Mohammad Ghassemi, Benjamin Moody, Peter Szolovits, Leo Anthony Celi, and Roger G Mark. 2016. [Mimic-iii, a freely accessible critical care database](https://md.research.elamur.ai/free/en/papers/johnson-2016-mimic-iii-freely-accessible-critical/). Scientific data, 3(1):1–9.
20. Oren Kalinsky, Guy Kushilevitz, Alexander Libov, and Yoav Goldberg. 2023. Simple and effective multi-token completion from masked language models. In Findings of the Association for Computational Linguistics: EACL 2023, pages 2356–2369, Dubrovnik, Croatia. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Oren+Kalinsky%2C+Guy+Kushilevitz%2C+Alexander+Libov%2C+and+Yoav+Goldberg%2E+2023%2E+Simple+and+effective+multi%2Dtoken+completion+from+masked+language+models%2E+In+Findings+of+the+Association+for+Computational+Ling)
21. Yuval Kirstain, Ori Ram, and Omer Levy. 2021. [Coreference resolution without span representations](https://md.research.elamur.ai/free/en/papers/kirstain-2021-coreference-resolution-without-span-representations/). In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers), pages 14–…
22. Alexey Kurakin, Natalia Ponomareva, Umar Syed, Liam MacDermed, and Andreas Terzis. 2023. Harnessing large-language models to generate private synthetic text. arXiv preprint arXiv:2306.01684. — [arXiv:2306.01684](https://arxiv.org/abs/2306.01684) [find](https://scholar.google.com/scholar?q=Alexey+Kurakin%2C+Natalia+Ponomareva%2C+Umar+Syed%2C+Liam+MacDermed%2C+and+Andreas+Terzis%2E+2023%2E+Harnessing+large%2Dlanguage+models+to+generate+private+synthetic+text%2E+arXiv+preprint+arXiv%3A2306%2E01684%2E+%E2%80%94+%5BarXiv%3A)
23. Pierre Lison, Ildikó Pilán, David Sanchez, Montserrat Batet, and Lilja Øvrelid. 2021. Anonymisation models for text data: State of the art, challenges and future directions. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Co… [find](https://scholar.google.com/scholar?q=Pierre+Lison%2C+Ildik%C3%B3+Pil%C3%A1n%2C+David+Sanchez%2C+Montserrat+Batet%2C+and+Lilja+%C3%98vrelid%2E+2021%2E+Anonymisation+models+for+text+data%3A+State+of+the+art%2C+challenges+and+future+directions%2E+In+Proceedings+of+the+59th)
24. Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. [Roberta: A robustly optimized bert pretraining approach](https://md.research.elamur.ai/free/en/papers/liu-2019-roberta-robustly-optimized-bert-pretraining/). arXiv preprint arXiv:1907.11692.
25. Nils Lukas, Ahmed Salem, Robert Sim, Shruti Tople, Lukas Wutschitz, and Santiago Zanella-Béguelin. 2023. Analyzing leakage of personally identifiable information in language models. In 2023 IEEE Symposium on Security and Privacy (SP), pages 346–363. [find](https://scholar.google.com/scholar?q=Nils+Lukas%2C+Ahmed+Salem%2C+Robert+Sim%2C+Shruti+Tople%2C+Lukas+Wutschitz%2C+and+Santiago+Zanella%2DB%C3%A9guelin%2E+2023%2E+Analyzing+leakage+of+personally+identifiable+information+in+language+models%2E+In+2023+IEEE+Sympo)
26. Nuno Mamede, Jorge Baptista, and Francisco Dias. 2016. Automated anonymization of text documents. In 2016 IEEE Congress on Evolutionary Computation (CEC), pages 1287–1294. [find](https://scholar.google.com/scholar?q=Nuno+Mamede%2C+Jorge+Baptista%2C+and+Francisco+Dias%2E+2016%2E+Automated+anonymization+of+text+documents%2E+In+2016+IEEE+Congress+on+Evolutionary+Computation+%28CEC%29%2C+pages+1287%E2%80%931294%2E)
27. Justus Mattern, Zhijing Jin, Benjamin Weggenmann, Bernhard Schoelkopf, and Mrinmaya Sachan. 2022. Differentially private language models for secure data sharing. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 4860–4873, Abu Dhabi, United Arab Emirate… [find](https://scholar.google.com/scholar?q=Justus+Mattern%2C+Zhijing+Jin%2C+Benjamin+Weggenmann%2C+Bernhard+Schoelkopf%2C+and+Mrinmaya+Sachan%2E+2022%2E+Differentially+private+language+models+for+secure+data+sharing%2E+In+Proceedings+of+the+2022+Conference+)
28. Omri Mendels, Coby Peled, Nava Vaisman Levy, Sharon Hart, Tomer Rosenthal, Limor Lahiani, et al. 2018. Microsoft Presidio: Context aware, pluggable and customizable pii anonymization service for text and images. [find](https://scholar.google.com/scholar?q=Omri+Mendels%2C+Coby+Peled%2C+Nava+Vaisman+Levy%2C+Sharon+Hart%2C+Tomer+Rosenthal%2C+Limor+Lahiani%2C+et+al%2E+2018%2E+Microsoft+Presidio%3A+Context+aware%2C+pluggable+and+customizable+pii+anonymization+service+for+text+)
29. Ishna Neamatullah, Margaret M Douglass, Li-Wei H Lehman, Andrew Reisner, Mauricio Villarroel, William J Long, Peter Szolovits, George B Moody, Roger G Mark, and Gari D Clifford. 2008. Automated de-identification of free-text medical records. BMC Med. Inform. Decis. Mak., 8(1):32. [find](https://scholar.google.com/scholar?q=Ishna+Neamatullah%2C+Margaret+M+Douglass%2C+Li%2DWei+H+Lehman%2C+Andrew+Reisner%2C+Mauricio+Villarroel%2C+William+J+Long%2C+Peter+Szolovits%2C+George+B+Moody%2C+Roger+G+Mark%2C+and+Gari+D+Clifford%2E+2008%2E+Automated+de%2Dide)
30. Bhanudas Suresh Panchbhai and Varsha Makarand Pathak. 2022. A systematic review of natural language processing in healthcare. Journal of Algebraic Statistics, 13(1):682–707. [find](https://scholar.google.com/scholar?q=Bhanudas+Suresh+Panchbhai+and+Varsha+Makarand+Pathak%2E+2022%2E+A+systematic+review+of+natural+language+processing+in+healthcare%2E+Journal+of+Algebraic+Statistics%2C+13%281%29%3A682%E2%80%93707%2E)
31. Ildikó Pilán, Pierre Lison, Lilja Øvrelid, Anthi Papadopoulou, David Sánchez, and Montserrat Batet. 2022. [The text anonymization benchmark (TAB): A dedicated corpus and evaluation framework for text anonymization](https://md.research.elamur.ai/free/en/papers/pilan-2022-text-anonymization-benchmark-tab-dedicated/). 48(4):1053–1101.
32. Computational Linguistics, David Pissarra, Isabel Curioso, João Alveira, Duarte Pereira, Bruno Ribeiro, Tomás Souper, Vasco Gomes, André Carreiro, and Vitor Rolla. 2024. Unlocking the potential of large language models for clinical text anonymization: A comparative study. In Proceedings of the Fifth… [find](https://scholar.google.com/scholar?q=Computational+Linguistics%2C+David+Pissarra%2C+Isabel+Curioso%2C+Jo%C3%A3o+Alveira%2C+Duarte+Pereira%2C+Bruno+Ribeiro%2C+Tom%C3%A1s+Souper%2C+Vasco+Gomes%2C+Andr%C3%A9+Carreiro%2C+and+Vitor+Rolla%2E+2024%2E+Unlocking+the+potential+of+lar)
33. Pranav Putta, Ander Steele, and Joseph W Ferrara. 2023. Differentially private conditional text generation for synthetic data production. [find](https://scholar.google.com/scholar?q=Pranav+Putta%2C+Ander+Steele%2C+and+Joseph+W+Ferrara%2E+2023%2E+Differentially+private+conditional+text+generation+for+synthetic+data+production%2E)
34. Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J. Liu. 2020. [Exploring the limits of transfer learning with a unified text-to-text transformer](https://md.research.elamur.ai/free/en/papers/raffel-2019-exploring-limits-transfer-learning-unified/). Journal of Machine Learning Research, 21(140):1–67.
35. Krithika Ramesh, Nupoor Gandhi, Pulkit Madaan, Lisa Bauer, Charith Peris, and Anjalie Field. 2024. Evaluating differentially private synthetic data generation in high-stakes domains. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 15254–15269, Miami, Florida, USA. Ass… [find](https://scholar.google.com/scholar?q=Krithika+Ramesh%2C+Nupoor+Gandhi%2C+Pulkit+Madaan%2C+Lisa+Bauer%2C+Charith+Peris%2C+and+Anjalie+Field%2E+2024%2E+Evaluating+differentially+private+synthetic+data+generation+in+high%2Dstakes+domains%2E+In+Findings+of+th)
36. Bruno Ribeiro, Vitor Rolla, and Ricardo Santos. 2023. INCOGNITUS: A toolbox for automated clinical notes anonymization. In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations, pages 187–194, Dubrovnik, Croatia. Associatio… [find](https://scholar.google.com/scholar?q=Bruno+Ribeiro%2C+Vitor+Rolla%2C+and+Ricardo+Santos%2E+2023%2E+INCOGNITUS%3A+A+toolbox+for+automated+clinical+notes+anonymization%2E+In+Proceedings+of+the+17th+Conference+of+the+European+Chapter+of+the+Association)
37. Patrick Ruch, Robert H. Baud, Anne-Marie Rassinoux, Pierrette Bouillon, and Gilbert Robert. 2000. Medical document anonymization with a semantic lexicon. Proceedings of American Medical Informatics Association Symposium, pages 729–733. [find](https://scholar.google.com/scholar?q=Patrick+Ruch%2C+Robert+H%2E+Baud%2C+Anne%2DMarie+Rassinoux%2C+Pierrette+Bouillon%2C+and+Gilbert+Robert%2E+2000%2E+Medical+document+anonymization+with+a+semantic+lexicon%2E+Proceedings+of+American+Medical+Informatics+As)
38. Victor Sanh, Lysandre Debut, Julien Chaumond, and Thomas Wolf. 2019. Distilbert, a distilled version of bert: smaller, faster, cheaper and lighter. In NeurIPS EMC^2 Workshop. [find](https://scholar.google.com/scholar?q=Victor+Sanh%2C+Lysandre+Debut%2C+Julien+Chaumond%2C+and+Thomas+Wolf%2E+2019%2E+Distilbert%2C+a+distilled+version+of+bert%3A+smaller%2C+faster%2C+cheaper+and+lighter%2E+In+NeurIPS+EMC%5E2+Workshop%2E)
39. Robin Staab, Mark Vero, Mislav Balunovic, and Martin Vechev. 2025. Language models are advanced anonymizers. In International Conference on Learning Representations, volume 2025, pages 98558– 98598. [find](https://scholar.google.com/scholar?q=Robin+Staab%2C+Mark+Vero%2C+Mislav+Balunovic%2C+and+Martin+Vechev%2E+2025%2E+Language+models+are+advanced+anonymizers%2E+In+International+Conference+on+Learning+Representations%2C+volume+2025%2C+pages+98558%E2%80%93+98598%2E)
40. Latanya Sweeney. 1996. Replacing personally-identifying information in medical records, the scrub system. Proceedings of Americal Medical Informatics Association Annual Fall Symposium, pages 333– 337. [find](https://scholar.google.com/scholar?q=Latanya+Sweeney%2E+1996%2E+Replacing+personally%2Didentifying+information+in+medical+records%2C+the+scrub+system%2E+Proceedings+of+Americal+Medical+Informatics+Association+Annual+Fall+Symposium%2C+pages+333%E2%80%93+337%2E)
41. Santosh T.y.s.s., Mahmoud Aly, and Matthias Grabmair. 2024. LexAbSumm: Aspect-based summarization of legal decisions. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 10422–10431, Torino, Italia. ELRA… [find](https://scholar.google.com/scholar?q=Santosh+T%2Ey%2Es%2Es%2E%2C+Mahmoud+Aly%2C+and+Matthias+Grabmair%2E+2024%2E+LexAbSumm%3A+Aspect%2Dbased+summarization+of+legal+decisions%2E+In+Proceedings+of+the+2024+Joint+International+Conference+on+Computational+Linguis)
42. Ozlem Uzuner, Andreea Bodnari, Shuying Shen, Tyler Forbush, John Pestian, and Brett R South. 2012. Evaluating the state of the art in coreference resolution for electronic medical records. Journal of the American Medical Informatics Association, 19(5):786–791. [find](https://scholar.google.com/scholar?q=Ozlem+Uzuner%2C+Andreea+Bodnari%2C+Shuying+Shen%2C+Tyler+Forbush%2C+John+Pestian%2C+and+Brett+R+South%2E+2012%2E+Evaluating+the+state+of+the+art+in+coreference+resolution+for+electronic+medical+records%2E+Journal+of+)
43. Arpita Vats, Zhe Liu, Peng Su, Debjyoti Paul, Yingyi Ma, Yutong Pang, Zeeshan Ahmed, and Ozlem Kalinli. 2024. Recovering from privacy-preserving masking with large language models. In ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 10771–10… [find](https://scholar.google.com/scholar?q=Arpita+Vats%2C+Zhe+Liu%2C+Peng+Su%2C+Debjyoti+Paul%2C+Yingyi+Ma%2C+Yutong+Pang%2C+Zeeshan+Ahmed%2C+and+Ozlem+Kalinli%2E+2024%2E+Recovering+from+privacy%2Dpreserving+masking+with+large+language+models%2E+In+ICASSP+2024+%2D+20)
44. Elena Volodina, Yousuf Ali Mohammed, Sandra Der-bring, Arild Matsson, and Beata Megyesi. 2020. Towards privacy by design in learner corpora research: A case of on-the-fly pseudonymization of Swedish learner essays. In Proceedings of the 28th International Conference on Computational Linguistics, pag… [find](https://scholar.google.com/scholar?q=Elena+Volodina%2C+Yousuf+Ali+Mohammed%2C+Sandra+Der%2Dbring%2C+Arild+Matsson%2C+and+Beata+Megyesi%2E+2020%2E+Towards+privacy+by+design+in+learner+corpora+research%3A+A+case+of+on%2Dthe%2Dfly+pseudonymization+of+Swedish+l)
45. Oleksandr Yermilov, Vipul Raheja, and Artem Chernodub. 2023. Privacy- and utility-preserving NLP with anonymized data: A case study of pseudonymization. In Proceedings of the 3rd Workshop on Trustworthy Natural Language Processing (TrustNLP 2023), pages 232–241, Toronto, Canada. Association for Comp… [find](https://scholar.google.com/scholar?q=Oleksandr+Yermilov%2C+Vipul+Raheja%2C+and+Artem+Chernodub%2E+2023%2E+Privacy%2D+and+utility%2Dpreserving+NLP+with+anonymized+data%3A+A+case+study+of+pseudonymization%2E+In+Proceedings+of+the+3rd+Workshop+on+Trustwort)
46. Xiang Yue, Minxin Du, Tianhao Wang, Yaliang Li, Huan Sun, and Sherman S. M. Chow. 2021. Differential privacy for text analytics via natural text sanitization. In Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pages 3853–3866, Online. Association for Computational Linguis… [find](https://scholar.google.com/scholar?q=Xiang+Yue%2C+Minxin+Du%2C+Tianhao+Wang%2C+Yaliang+Li%2C+Huan+Sun%2C+and+Sherman+S%2E+M%2E+Chow%2E+2021%2E+Differential+privacy+for+text+analytics+via+natural+text+sanitization%2E+In+Findings+of+the+Association+for+Comput)
47. Amber Stubbs, Michele Filannino, and Özlem Uzuner. 2017. De-identification of psychiatric intake records: Overview of 2016 cegs n-grid shared tasks track 1. Journal of Biomedical Informatics, 75:S4–S18. [find](https://scholar.google.com/scholar?q=Amber+Stubbs%2C+Michele+Filannino%2C+and+%C3%96zlem+Uzuner%2E+2017%2E+De%2Didentification+of+psychiatric+intake+records%3A+Overview+of+2016+cegs+n%2Dgrid+shared+tasks+track+1%2E+Journal+of+Biomedical+Informatics%2C+75%3AS4%E2%80%93S1)
48. Xiang Yue, Huseyin Inan, Xuechen Li, Girish Kumar, Julia McAnallen, Hoda Shajari, Huan Sun, David Levitan, and Robert Sim. 2023. Synthetic text generation with differential privacy: A simple and practical recipe. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguist… [find](https://scholar.google.com/scholar?q=Xiang+Yue%2C+Huseyin+Inan%2C+Xuechen+Li%2C+Girish+Kumar%2C+Julia+McAnallen%2C+Hoda+Shajari%2C+Huan+Sun%2C+David+Levitan%2C+and+Robert+Sim%2E+2023%2E+Synthetic+text+generation+with+differential+privacy%3A+A+simple+and+pract)
49. Amber Stubbs and Özlem Uzuner. 2015. Annotating longitudinal clinical narratives for de-identification. Journal of Biomedical Informatics, 58:S20–S29. [find](https://scholar.google.com/scholar?q=Amber+Stubbs+and+%C3%96zlem+Uzuner%2E+2015%2E+Annotating+longitudinal+clinical+narratives+for+de%2Didentification%2E+Journal+of+Biomedical+Informatics%2C+58%3AS20%E2%80%93S29%2E)
50. Haoxi Zhong, Chaojun Xiao, Cunchao Tu, Tianyang Zhang, Zhiyuan Liu, and Maosong Sun. 2020. [How does NLP benefit legal system: A summary of legal artificial intelligence](https://md.research.elamur.ai/free/en/papers/zhong-2020-how-does-nlp-benefit-legal/). In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 5218–5230, Online. Association f…

*Updated 31 October 2026*