Conference paper · 2024 · Open access
Fine-Tuning Language Models with Differential Privacy through Adaptive Noise Allocation
Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP), 8368–8375 · Published 1 January 2024 · DOI 10.18653/v1/2024.findings-emnlp.491
In brief
“Fine-Tuning Language Models with Differential Privacy through Adaptive Noise Allocation” is a 2024 conference paper by Xianzhi Li and 4 co-authors, published in Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP). OpenAlex counts 24 citations as of 19 November 2026, which puts it in the top 2% of works published in 2024 by citations. It is open access under a CC BY licence: the full text is free to read at Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP).
- Citations
- 24
- Most cited in
- 2026 (13)
- Field-weighted impact
- 2.29
- References
- 27
- Authors
- 5
Abstract
Language models are capable of memorizing detailed patterns and information, leading to a double-edged effect: they achieve impressive modeling performance on downstream tasks with the stored knowledge but also raise significant privacy concerns.Traditional differential privacy based training approaches offer robust safeguards by employing a uniform noise distribution across all parameters.However, this overlooks the distinct sensitivities and contributions of individual parameters in privacy protection and often results in suboptimal models.To address these limitations, we propose ANADP, a novel algorithm that adaptively allocates additive noise based on the importance of model parameters.We demonstrate that ANADP narrows the performance gap between regular fine-tuning and traditional DP-SGD based fine-tuning on a series of datasets while maintaining the required privacy constraints.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Li, X., Zmigrod, R., Ma, Z., Liu, X., & Zhu, X. (2024). Fine-Tuning Language Models with Differential Privacy through Adaptive Noise Allocation. Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP), 8368–8375. https://doi.org/10.18653/v1/2024.findings-emnlp.491
MLA 9
Li, Xianzhi, et al. “Fine-Tuning Language Models with Differential Privacy through Adaptive Noise Allocation.” Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP), 2024, pp. 8368–8375. https://doi.org/10.18653/v1/2024.findings-emnlp.491.
Chicago
Li, Xianzhi, Ran Zmigrod, Zhiqiang Ma, Xiaomo Liu, and Xiaodan Zhu. 2024. “Fine-Tuning Language Models with Differential Privacy through Adaptive Noise Allocation.” Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP): 8368–8375. https://doi.org/10.18653/v1/2024.findings-emnlp.491.
Harvard
Li, X. et al. (2024) ‘Fine-Tuning Language Models with Differential Privacy through Adaptive Noise Allocation’, Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP), pp. 8368–8375. doi:10.18653/v1/2024.findings-emnlp.491.
IEEE
X. Li, R. Zmigrod, Z. Ma, X. Liu, and X. Zhu, “Fine-Tuning Language Models with Differential Privacy through Adaptive Noise Allocation,” Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP), pp. 8368–8375, 2024, doi: 10.18653/v1/2024.findings-emnlp.491.
BibTeX
@inproceedings{li2024fine,
title = {{Fine-Tuning Language Models with Differential Privacy through Adaptive Noise Allocation}},
author = {Li, Xianzhi and Zmigrod, Ran and Ma, Zhiqiang and Liu, Xiaomo and Zhu, Xiaodan},
booktitle = {Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)},
year = {2024},
pages = {8368--8375},
doi = {10.18653/v1/2024.findings-emnlp.491},
url = {https://doi.org/10.18653/v1/2024.findings-emnlp.491}
}
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
- language model fine-tuning
- parameter sensitivity
- DP-SGD
- privacy-preserving machine learning
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?
Li, X., Zmigrod, R., Ma, Z., Liu, X., & Zhu, X. (2024). Fine-Tuning Language Models with Differential Privacy through Adaptive Noise Allocation. Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP), 8368–8375. https://doi.org/10.18653/v1/2024.findings-emnlp.491
How many times has this paper been cited?
24 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 Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP): sign in and open the PDF from this page.
Who wrote this paper?
Xianzhi Li, Ran Zmigrod, Zhiqiang Ma, Xiaomo Liu, Xiaodan Zhu.
What is the DOI of this paper?
10.18653/v1/2024.findings-emnlp.491, permanently at https://doi.org/10.18653/v1/2024.findings-emnlp.491. 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.