Revisiting Privacy, Utility, and Efficiency Trade-offs when Fine-Tuning Large Language Models
This work addresses privacy concerns for users and developers of large language models by showing that efficient fine-tuning can enhance privacy without sacrificing utility, though it is incremental as it builds on existing methods.
The paper investigates the trade-offs between privacy, utility, and efficiency in fine-tuning large language models, finding that efficient methods like LoRA can mitigate privacy risks similarly to private methods like DP, contradicting the common belief that privacy and efficiency are conflicting goals.
We study the inherent trade-offs in minimizing privacy risks and maximizing utility, while maintaining high computational efficiency, when fine-tuning large language models (LLMs). A number of recent works in privacy research have attempted to mitigate privacy risks posed by memorizing fine-tuning data by using differentially private training methods (e.g., DP), albeit at a significantly higher computational cost (inefficiency). In parallel, several works in systems research have focussed on developing (parameter) efficient fine-tuning methods (e.g., LoRA), but few works, if any, investigated whether such efficient methods enhance or diminish privacy risks. In this paper, we investigate this gap and arrive at a surprising conclusion: efficient fine-tuning methods like LoRA mitigate privacy risks similar to private fine-tuning methods like DP. Our empirical finding directly contradicts prevailing wisdom that privacy and efficiency objectives are at odds during fine-tuning. Our finding is established by (a) carefully defining measures of privacy and utility that distinguish between memorizing sensitive and non-sensitive tokens in training and test datasets used in fine-tuning and (b) extensive evaluations using multiple open-source language models from Pythia, Gemma, and Llama families and different domain-specific datasets.