Saved in:
Bibliographic Details
Main Authors: Wang, Fei, Li, Baochun
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.20856
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915359574982656
author Wang, Fei
Li, Baochun
author_facet Wang, Fei
Li, Baochun
contents Memorization in large language models (LLMs) makes them vulnerable to data extraction attacks. While pre-training memorization has been extensively studied, fewer works have explored its impact in fine-tuning, particularly for LoRA fine-tuning, a widely adopted parameter-efficient method. In this work, we re-examine memorization in fine-tuning and uncover a surprising divergence from prior findings across different fine-tuning strategies. Factors such as model scale and data duplication, which strongly influence memorization in pre-training and full fine-tuning, do not follow the same trend in LoRA fine-tuning. Using a more relaxed similarity-based memorization metric, we demonstrate that LoRA significantly reduces memorization risks compared to full fine-tuning, while still maintaining strong task performance.
format Preprint
id arxiv_https___arxiv_org_abs_2506_20856
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Leaner Training, Lower Leakage: Revisiting Memorization in LLM Fine-Tuning with LoRA
Wang, Fei
Li, Baochun
Machine Learning
Computation and Language
Cryptography and Security
Memorization in large language models (LLMs) makes them vulnerable to data extraction attacks. While pre-training memorization has been extensively studied, fewer works have explored its impact in fine-tuning, particularly for LoRA fine-tuning, a widely adopted parameter-efficient method. In this work, we re-examine memorization in fine-tuning and uncover a surprising divergence from prior findings across different fine-tuning strategies. Factors such as model scale and data duplication, which strongly influence memorization in pre-training and full fine-tuning, do not follow the same trend in LoRA fine-tuning. Using a more relaxed similarity-based memorization metric, we demonstrate that LoRA significantly reduces memorization risks compared to full fine-tuning, while still maintaining strong task performance.
title Leaner Training, Lower Leakage: Revisiting Memorization in LLM Fine-Tuning with LoRA
topic Machine Learning
Computation and Language
Cryptography and Security
url https://arxiv.org/abs/2506.20856