计算机与数字工程2025，Vol.53Issue(2)：493-498,6.DOI:10.3969/j.issn.1672-9722.2025.02.034
基于差分隐私的大语言模型指令微调技术
Instruction Fine tuning Techniques for Large Language Models Based on Differential Privacy
摘要
Abstract
Due to the large amount of data information required for large language models,privacy data leakage often occurs when designing instruction fine-tuning techniques for large language models,resulting in poor fine-tuning performance of the tech-nology.In response,a large language model instruction fine-tuning technique based on differential privacy is proposed.Under the influence of differential privacy,this paper calculates the sensitivity of the instruction dataset,then calculates the size of the intro-duced random noise,and adds random noise to the instruction dataset.This paper reads a large number of model parameters from it,sets the loss function of the model,updates the model parameters through gradient values,and calculates the model instruction fine-tuning parameters.By calculating the evaluation value of the model,the performance of the model after initial fine-tuning is de-termined.Then,a low rank matrix is introduced to perform secondary fine-tuning on the large language model,achieving perfor-mance optimization of the model.The experimental results show that the designed fine-tuning technique has an average perplexity of 0.35 in practical applications,indicating good fine-tuning performance.关键词
差分隐私/大语言模型/指令微调/微调策略/微调参数/数据隐私/随机噪声Key words
differential privacy/large language model(LLM)/instruction fine-tuning/fine tuning strategy/fine tuning pa-rameters/data privacy/random noise分类
计算机与自动化引用本文复制引用
蒋金陵,徐胜超,杨波,毛明扬,蒋大锐..基于差分隐私的大语言模型指令微调技术[J].计算机与数字工程,2025,53(2):493-498,6.基金项目
国家自然科学基金面上项目(编号:61972444) （编号:61972444）
广州华商学院校内科研导师制项目(编号:2023HSDS28)资助. （编号:2023HSDS28）
