An Empirical Analysis of Memorization in Fine-tuned Autoregressive Language Models
Open accessThe DOI matches its Crossref record; 12 of the 12 references it cites were found in a registry or an index.
Abstract
Several recent works have shown that large language models present privacy risks through memorization of training data.Little attention, however, has been given to the fine-tuning phase and it is not well understood how memorization risk varies across different fine-tuning methods (such as fine-tuning the full model, the model head, and adapter).This presents increasing concern as the "pre-train and fine-tune" paradigm proliferates.We empirically study memorization of fine-tuning methods using membership inference and extraction attacks, and show that their susceptibility to attacks is very different.We observe that fine-tuning the head of the model has the highest susceptibility to attacks, whereas fine-tuning smaller adapters appears to be less vulnerable to known extraction attacks.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Language Models are Few-Shot Learners
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.14165 · Cited by 23,372
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
Raffel, C., Shazeer, N., Roberts, A., Lee, K., Narang, S., Matena, M., Zhou, Y., Li, W., & Liu, P. J. (2019) · arXiv · doi:10.48550/arxiv.1910.10683 · Cited by 10,929
Lewis, M., Liu, Y., Goyal, N., Ghazvininejad, M., Mohamed, A., Levy, O., Stoyanov, V., & Zettlemoyer, L. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.703 · Cited by 8,821
Lewis, M., Liu, Y., Goyal, N., Ghazvininejad, M., Mohamed, A., Levy, O., Stoyanov, V., & Zettlemoyer, L. (2019) · arXiv · doi:10.48550/arxiv.1910.13461 · Cited by 8,816
Building a Large Annotated Corpus of English: The Penn Treebank
Marcus, M. (1993) · doi:10.21236/ada273556 · Cited by 7,405
Prefix-Tuning: Optimizing Continuous Prompts for Generation
Li, X. L., & Liang, P. (2021) · Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) · doi:10.18653/v1/2021.acl-long.353 · Cited by 2,473
Evaluating Large Language Models Trained on Code
Chen, M., Tworek, J., Jun, H., Yuan, Q., Pinto, H. P. D. O., Kaplan, J., Edwards, H., Burda, Y., Joseph, N., Brockman, G., et al. (2021) · arXiv · doi:10.48550/arxiv.2107.03374 · Cited by 1,436
Extracting Training Data from Large Language Models
Carlini, N., Tramer, F., Wallace, E., Jagielski, M., Herbert-Voss, A., Lee, K., Roberts, A., Brown, T., Song, D., Erlingsson, U., et al. (2020) · arXiv · doi:10.48550/arxiv.2012.07805 · Cited by 727 · cited 5×
“Several works have demonstrated that such large models have a high capacity for memorizing training samples during pre-training and are therefore highly susceptible to membership inference and data extraction attacks (Zanella-Béguelin et al., 2020; Carlini et al., 2021b; Nakamura et al., 2021).”
BackgroundMethodInfluentialThe Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networks
Carlini, N., Liu, C., Erlingsson, Ú., Kos, J., & Song, D. (2018) · arXiv · doi:10.48550/arxiv.1802.08232 · Cited by 629
What Does it Mean for a Language Model to Preserve Privacy?
Brown, H., Lee, K., Mireshghallah, F., Shokri, R., & Tramèr, F. (2022) · 2022 ACM Conference on Fairness Accountability and Transparency · doi:10.1145/3531146.3534642 · Cited by 165
Self-citation
Cited by
A survey on large language model (LLM) security and privacy: The Good, The Bad, and The Ugly
Yao, Y., Duan, J., Xu, K., Cai, Y., Sun, Z., & Zhang, Y. (2024) · High-Confidence Computing · doi:10.1016/j.hcc.2024.100211 · Cited by 1,083
“Mireshghallah et al. [183] found that fine-tuning the head of the model exhibits greater susceptibility to attacks when compared to fine-tuning smaller adapters.”
BackgroundLarge Language Models for Cyber Security: A Systematic Literature Review
Xu, H., Wang, S., Li, N., Wang, K., Zhao, Y., Chen, K., Yu, T., Liu, Y., & Wang, H. (2025) · ACM Transactions on Software Engineering and Methodology · doi:10.1145/3769676 · Cited by 189
The Good and The Bad: Exploring Privacy Issues in Retrieval-Augmented Generation (RAG)
Zeng, S., Zhang, J., He, P., Liu, Y., Xing, Y., Xu, H., Ren, J., Chang, Y., Wang, S., Yin, D., et al. (2024) · Findings of the Association for Computational Linguistics ACL 2024 · doi:10.18653/v1/2024.findings-acl.267 · Cited by 149
Experimental narratives: A comparison of human crowdsourced storytelling and AI storytelling
Beguš, N. (2024) · Humanities and Social Sciences Communications · doi:10.1057/s41599-024-03868-8 · Cited by 60
LLM-PBE: Assessing Data Privacy in Large Language Models
Li, Q., Hong, J., Xie, C., Tan, J., Xin, R., Hou, J., Yin, X., Wang, Z., Hendrycks, D., Wang, Z., et al. (2024) · Proceedings of the VLDB Endowment · doi:10.14778/3681954.3681994 · Cited by 42
Metadata
- Authors
- Mireshghallah, F., Uniyal, A., Wang, T., Evans, D., & Berg-Kirkpatrick, T.
- Venue
- Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
- Published
- 2022
- Pages
- 1816-1826
- OpenAlex
- W4385573004
- Cited by
- 47
- References
- 12
- FWCI
- 5.54
- Type
- conference paper
- Language
- en
- Open access
- hybrid
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: An Empirical Analysis of Memorization in Fine-tuned Autoregressive Language Models. https://app.cochat.ai/papers/10.18653/v1/2022.emnlp-main.119
- The paper
- Mireshghallah, F., Uniyal, A., Wang, T., Evans, D., & Berg-Kirkpatrick, T. (2022). An Empirical Analysis of Memorization in Fine-tuned Autoregressive Language Models. Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing. https://doi.org/10.18653/v1/2022.emnlp-main.119
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.