Fetching the paper…
Reading the bibliography…
Parameter-Efficient Fine-Tuning (PEFT) provides a practical way for users to customize Large Language Models (LLMs) with their private data in LLM service scenarios.
T. Brown, B. Mann, N. Ryder, M. Subbiah, J. D. Kaplan, P. Dhariwal, A. Neelakantan, P. Shyam, G. Sastry, A. Askell et al. , “Language models are few-shot learners,” in Proceedings of NeurIPS , 2020, pp. 1877–1901
1901
Earlier work this paper cites.
A. Evfimievski, J. Gehrke, and R. Srikant, “Limiting privacy breaches in privacy preserving data mining,” in Proceeding of SIGMOD-SIGACT-SIGART , 2003, pp. 211–222
2003
Earlier work this paper cites.
K. Chatzikokolakis, M. E. Andrés, N. E. Bordenabe, and C. Palamidessi, “Broadening the scope of differential privacy using metrics,” in Privacy Enhancing Technologies , 2013, pp. 82–102
2013
Earlier work this paper cites.
R. Socher, A. Perelygin, J. Wu, J. Chuang, C. D. Manning, A. Y. Ng, and C. Potts, “Recursive deep models for semantic compositionality over a sentiment treebank,” in Proceedings of EMNLP , 2013, pp. 1631–1642
2013
Earlier work this paper cites.
D. Hovy, A. Johannsen, and A. Søgaard, “User review sites as a resource for large-scale sociolinguistic studies,” in Proceedings of TheWebConf , 2015, pp. 452–461
2015
Earlier work this paper cites.
D. P. Kingma and J. Ba, “Adam: A method for stochastic optimization,” in Proceedings of ICLR , 2015
2015
Earlier work this paper cites.
K. Martin and H. Nissenbaum, “Measuring privacy: An empirical test using context to expose confounding variables,” Columbia Science & Technology Law Review , vol. 18, pp. 176–218, 2016. [Online]. Available: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=2709584
2016
Earlier work this paper cites.
European Union, “Regulation (eu) 2016/679 of the european parliament and of the council,” OJ L 119 , pp. 1–88, 2016. [Online]. Available: https://eur-lex.europa.eu/eli/reg/2016/679/oj
2016
Earlier work this paper cites.
V. Bindschaedler, R. Shokri, and C. A. Gunter, “Plausible deniability for privacy-preserving data synthesis,” Proceedings of the VLDB Endowment , vol. 10, p. 481–492, 2017
2017
Earlier work this paper cites.
DataCanary, hilfialkaff, L. Jiang, M. Risdal, N. Dandekar, and tomtung, “Quora question pairs,” https://kaggle.com/competitions/quora-question-pairs , 2017, kaggle
2017
Earlier work this paper cites.
C. Gardent, A. Shimorina, S. Narayan, and L. Perez-Beltrachini, “The webnlg challenge: Generating text from rdf data,” in Proceedings of the International Conference on Natural Language Generation , 2017, pp. 124–133
2017
Earlier work this paper cites.
S. L. Pardau, “The california consumer privacy act: Towards a european-style privacy regime in the united states?” Journal of Technology Law & Policy , vol. 23, pp. 68–113, 2018. [Online]. Available: https://scholarship.law.ufl.edu/jtlp/vol23/iss1/2
2018
Earlier work this paper cites.
M. Coavoux, S. Narayan, and S. B. Cohen, “Privacy-preserving neural representations of text,” in Proceedings of EMNLP , 2018, pp. 1–10. [Online]. Available: https://aclanthology.org/D18-1001
2018
Earlier work this paper cites.
J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova, “BERT: Pre-training of deep bidirectional transformers for language understanding,” in Proceedings of ACL , 2019, pp. 4171–4186. [Online]. Available: https://aclanthology.org/N19-1423
2019
Earlier work this paper cites.
S. Sreekumar and D. Gündüz, “Optimal privacy-utility trade-off under a rate constraint,” in Proceedings of ISIT , 2019, pp. 2159–2163
2019
Earlier work this paper cites.
E. Voita, R. Sennrich, and I. Titov, “The bottom-up evolution of representations in the transformer: A study with machine translation and language modeling objectives,” in Proceedings of ACL , 2019, pp. 4396–4406. [Online]. Available: https://aclanthology.org/D19-1448
2019
Earlier work this paper cites.
I. Loshchilov and F. Hutter, “Decoupled weight decay regularization,” in Proceedings of ICLR , 2019. [Online]. Available: https://openreview.net/forum?id=Bkg6RiCqY7
2019
Earlier work this paper cites.
L. Lyu, X. He, and Y. Li, “Differentially private representation for NLP: Formal guarantee and an empirical study on privacy and fairness,” in Findings of EMNLP , 2020, pp. 2355–2365. [Online]. Available: https://aclanthology.org/2020.findings-emnlp.213
2020
Earlier work this paper cites.
O. Feyisetan, B. Balle, T. Drake, and T. Diethe, “Privacy-and utility-preserving textual analysis via calibrated multivariate perturbations,” in Proceedings of WSDM , 2020, pp. 178–186
2020
Cited alongside, same era.
J. Mamou, H. Le, M. Del Rio, C. Stephenson, H. Tang, Y. Kim, and S. Chung, “Emergence of separable manifolds in deep language representations,” in Proceedings of ICML , 2020
2020
Cited alongside, same era.
G. Kerrigan, D. Slack, and J. Tuyls, “Differentially private language models benefit from public pre-training,” in Proceedings of the Second Workshop on Privacy in NLP , 2020, pp. 39–45. [Online]. Available: https://aclanthology.org/2020.privatenlp-1.5
2020
Cited alongside, same era.
Y. Huang, Z. Song, D. Chen, K. Li, and S. Arora, “Texthide: Tackling data privacy in language understanding tasks,” in Findings of EMNLP , 2020, pp. 1368–1382
2020
Cited alongside, same era.
X. Li, F. Tramer, P. Liang, and T. Hashimoto, “Large language models can be strong differentially private learners,” in Proceedings of ICLR , 2022. [Online]. Available: https://openreview.net/forum?id=bVuP3ltATMz
2022
Later among the works it cites.
W. Shi, R. Shea, S. Chen, C. Zhang, R. Jia, and Z. Yu, “Just fine-tune twice: Selective differential privacy for large language models,” in Proceedings of EMNLP , 2022, pp. 6327–6340. [Online]. Available: https://aclanthology.org/2022.emnlp-main.425
2022
Later among the works it cites.
Z. Yang and Y. Liu, “On robust prefix-tuning for text classification,” in Proceedings of ICLR , 2022. [Online]. Available: https://openreview.net/forum?id=eBCmOocUejf
2022
Later among the works it cites.
X. Liu, K. Ji, Y. Fu, W. Tam, Z. Du, Z. Yang, and J. Tang, “P-tuning: Prompt tuning can be comparable to fine-tuning across scales and tasks,” in Proceedings of ACL , 2022, pp. 61–68. [Online]. Available: https://aclanthology.org/2022.acl-short.8
2022
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
C. Song and A. Raghunathan, “Information leakage in embedding models,” in Proceedings of ACM SIGSAC , 2020, pp. 377–390
2020
Cited alongside, same era.
J. Lee, W. Yoon, S. Kim, D. Kim, S. Kim, C. H. So, and J. Kang, “Biobert: a pre-trained biomedical language representation model for biomedical text mining,” Bioinformatics , vol. 36, no. 4, pp. 1234–1240, 2020
2020
Cited alongside, same era.
X. L. Li and P. Liang, “Prefix-tuning: Optimizing continuous prompts for generation,” in Proceedings of ACL , 2021, pp. 4582–4597. [Online]. Available: https://aclanthology.org/2021.acl-long.353
2021
Cited alongside, same era.
B. Lester, R. Al-Rfou, and N. Constant, “The power of scale for parameter-efficient prompt tuning,” in Proceedings of EMNLP , 2021, pp. 3045–3059. [Online]. Available: https://aclanthology.org/2021.emnlp-main.243
2021
Cited alongside, same era.
S. Hoory, A. Feder, A. Tendler, S. Erell, A. Peled-Cohen, I. Laish, H. Nakhost, U. Stemmer, A. Benjamini, A. Hassidim et al. , “Learning and evaluating a differentially private pre-trained language model,” in Findings of EMNLP , 2021, pp. 1178–1189. [Online]. Available: https://aclanthology.org/2021.findings-emnlp.102
2021
Cited alongside, same era.
N. Carlini, F. Tramer, E. Wallace, M. Jagielski, A. Herbert-Voss, K. Lee, A. Roberts, T. Brown, D. Song, U. Erlingsson et al. , “Extracting training data from large language models,” in USENIX Security , 2021, pp. 2633–2650
2021
Cited alongside, same era.
D. Yu, H. Zhang, W. Chen, J. Yin, and T.-Y. Liu, “Large scale private learning via low-rank reparametrization,” in Proceedings of ICML , 2021, pp. 12 208–12 218
2021
Cited alongside, same era.
C. Qu, W. Kong, L. Yang, M. Zhang, M. Bendersky, and M. Najork, “Natural language understanding with privacy-preserving bert,” in Proceedings of the CIKM , 2021, p. 1488–1497
2021
Cited alongside, same era.
Later among the works it cites.
S. Arnold, D. Yesilbas, and S. Weinzierl, “Guiding text-to-text privatization by syntax,” in Proceedings of TrustNLP , Jul. 2023, pp. 151–162. [Online]. Available: https://aclanthology.org/2023.trustnlp-1.14
2023
Closest in time.
A. Wettig, T. Gao, Z. Zhong, and D. Chen, “Should you mask 15% in masked language modeling?” in Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics , 2023, pp. 2985–3000. [Online]. Available: https://aclanthology.org/2023.eacl-main.217
2023
Closest in time.
N. Lukas, A. Salem, R. Sim, S. Tople, L. Wutschitz, and S. Zanella-Béguelin, “Analyzing leakage of personally identifiable information in language models,” in IEEE Symposium on Security and Privacy , 2023, pp. 346–363
2023
Closest in time.
2023
Closest in time.
J. Ye, Z. Zhu, F. Liu, R. Shokri, and V. Cevher, “Initialization matters: Privacy-utility analysis of overparameterized neural networks,” in Proceddings of NeurIPS , 2024
2024
Closest in time.
A. Zhang, Y. Wang, and S. Guo, “On the utility-informativeness-security trade-off in discrete task-oriented semantic communication,” IEEE Communications Letters , 2024
2024
Closest in time.
Y. Ding, X. Wu, Y. Meng, Y. Luo, H. Wang, and W. Pan, “Delving into differentially private transformer,” in Proceedings of ICML , 2024
2024
Closest in time.
R. Ye, W. Wang, J. Chai, D. Li, Z. Li, Y. Xu, Y. Du, Y. Wang, and S. Chen, “Openfedllm: Training large language models on decentralized private data via federated learning,” in Proceedings of the SIGKDD , 2024, pp. 6137–6147
2024
Closest in time.
2024
Closest in time.
Y. Yang, H. Wu, and H. Zhao, “Attack named entity recognition by entity boundary interference,” in Proceedings of COLING , 2024, pp. 1734–1744. [Online]. Available: https://aclanthology.org/2024.lrec-main.153
2024
Closest in time.
A. Dubey, A. Jauhri, A. Pandey, A. Kadian, A. Al-Dahle, A. Letman, A. Mathur, and Others, “The llama 3 herd of models,” arXiv preprint arXiv.2407.21783 , 2024
2024
Closest in time.
T. Dettmers, A. Pagnoni, A. Holtzman, and L. Zettlemoyer, “Qlora: Efficient finetuning of quantized llms,” Proceedings of NeurIPS , vol. 36, 2024
2024
Closest in time.
X. Shen, Y. Liu, Y. Liu, P. Wang, H. Liu, J. Hong, B. Duan, Z. Huang, Y. Mao, Y. Wu, and S. Zhong, “Sap: Privacy-preserving fine-tuning on language models with split-and-privatize framework,” in Proceedings of IJCAI , 2025, pp. 502–510. [Online]. Available: https://doi.org/10.24963/ijcai.2025/57
2025
Closest in time.