Leaner Training, Lower Leakage: Revisiting Memorization in LLM Fine-Tuning with LoRA
This addresses data extraction vulnerabilities in LLMs for users employing parameter-efficient fine-tuning, though it is incremental as it builds on prior memorization studies.
The paper tackled the problem of data memorization in large language models during fine-tuning, particularly with LoRA, and found that LoRA significantly reduces memorization risks compared to full fine-tuning while maintaining strong task performance.
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.