Preprint · 2025 · Open access

Assessing and Mitigating Data Memorization Risks in Fine-Tuned Large Language Models

Badrinath Ramakrishnan, Akshaya Balaji

arXiv (Cornell University) · Published 10 August 2025 · DOI 10.48550/arxiv.2508.14062

Open PDFView at the publisherCite this paper

In brief

“Assessing and Mitigating Data Memorization Risks in Fine-Tuned Large Language Models” is a 2025 preprint by Badrinath Ramakrishnan and Akshaya Balaji, published in arXiv (Cornell University). OpenAlex counts 6 citations as of 19 November 2026. It is open access: the full text is free to read at arXiv (Cornell University).

Citations
6
Most cited in
2026 (4)
References
16
Authors
2

Abstract

Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse natural language processing tasks, but their tendency to memorize training data poses significant privacy risks, particularly during fine-tuning processes. This paper presents a comprehensive empirical analysis of data memorization in fine-tuned LLMs and introduces a novel multi-layered privacy protection framework. Through controlled experiments on modern LLM architectures including GPT-2, Phi-3, and Gemma-2, we demonstrate that fine-tuning with repeated sensitive data increases privacy leakage rates from baseline levels of 0-5% to 60-75%, representing a 64.2% average increase across tested models. We propose and rigorously evaluate four complementary privacy protection methods: semantic data deduplication, differential privacy during generation, entropy-based filtering, and pattern-based content filtering. Our experimental results show that these techniques can reduce data leakage to 0% while maintaining 94.7% of original model utility.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Ramakrishnan, B., & Balaji, A. (2025). Assessing and Mitigating Data Memorization Risks in Fine-Tuned Large Language Models. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2508.14062

MLA 9

Ramakrishnan, Badrinath, and Akshaya Balaji. “Assessing and Mitigating Data Memorization Risks in Fine-Tuned Large Language Models.” arXiv (Cornell University), 2025. https://doi.org/10.48550/arxiv.2508.14062.

Chicago

Ramakrishnan, Badrinath and Akshaya Balaji. 2025. “Assessing and Mitigating Data Memorization Risks in Fine-Tuned Large Language Models.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2508.14062.

Harvard

Ramakrishnan, B. and Balaji, A. (2025) ‘Assessing and Mitigating Data Memorization Risks in Fine-Tuned Large Language Models’, arXiv (Cornell University). doi:10.48550/arxiv.2508.14062.

IEEE

B. Ramakrishnan and A. Balaji, “Assessing and Mitigating Data Memorization Risks in Fine-Tuned Large Language Models,” arXiv (Cornell University), 2025, doi: 10.48550/arxiv.2508.14062.

BibTeX

@misc{ramakrishnan2025assessing,
  title     = {{Assessing and Mitigating Data Memorization Risks in Fine-Tuned Large Language Models}},
  author    = {Ramakrishnan, Badrinath and Balaji, Akshaya},
  howpublished = {arXiv (Cornell University)},
  year      = {2025},
  doi       = {10.48550/arxiv.2508.14062},
  url       = {https://doi.org/10.48550/arxiv.2508.14062}
}

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

  • data memorization
  • large language models
  • fine-tuning
  • privacy leakage
  • privacy preservation
  • differential privacy
  • entropy-based filtering
  • sensitive data

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Ramakrishnan, B., & Balaji, A. (2025). Assessing and Mitigating Data Memorization Risks in Fine-Tuned Large Language Models. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2508.14062

How many times has this paper been cited?

6 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 arXiv (Cornell University): sign in and open the PDF from this page.

Who wrote this paper?

Badrinath Ramakrishnan, Akshaya Balaji.

What is the DOI of this paper?

10.48550/arxiv.2508.14062, permanently at https://doi.org/10.48550/arxiv.2508.14062. 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.