比较检索增强与参数高效微调在大语言模型隐私保护个性化中的应用
Comparing Retrieval-Augmentation and Parameter-Efficient Fine-Tuning for Privacy-Preserving Personalization of Large Language Models
AI总结：
本文首次系统比较了基于RAG和PEFT的大语言模型隐私保护个性化方法，发现RAG更适合冷启动用户，PEFT在数据充足时更优，两者结合可进一步提升性能。
摘要：
尽管隐私保护方法对各种搜索、推荐和问答任务产生了重大影响，但针对大语言模型（LLM）个性化的隐私保护方法探索相对有限。该领域有一种主要方法，即通过检索增强生成（RAG），通过从用户个人数据中检索信息来丰富输入提示，从而生成个性化输出。本文研究了一种与RAG正交的方法，该方法通过参数高效微调（PEFT）来学习依赖用户的LLM参数。本文首次系统性地探索了PEFT在LLM个性化中的应用，并在来自LaMP基准的七个不同数据集上对基于RAG和PEFT的解决方案进行了广泛比较。结果显示，平均而言，基于RAG和PEFT的个性化方法分别比非个性化LLM提升了14.92%和1.07%。当结合RAG与PEFT时，我们观察到进一步提升15.98%，突显了两者集成在增强个性化文本生成方面的有效性。此外，我们发现可用用户数据量与PEFT的有效性之间存在正相关。这一发现表明，RAG对冷启动用户（即个人数据有限的用户）特别有益，而PEFT在拥有更多用户特定数据时表现更好。
英文摘要：
Despite its substantial impact on various search, recommendation, and question answering tasks, privacy-preserving methods for personalizing large language models (LLMs) have received relatively limited exploration. There is one primary approach in this area through retrieval-augmented generation (RAG), which generates personalized outputs by enriching the input prompt with information retrieved from the user's personal data. This paper studies an orthogonal approach to RAG that involves learning user-dependent LLM parameters through parameter-efficient fine-tuning (PEFT). This paper presents the first systematic study for exploration of PEFT for LLM personalization and provides an extensive comparisons between RAG- and PEFT-based solutions, across a broad set of seven diverse datasets from the LaMP benchmark. Our results demonstrate that, on average, both RAG- and PEFT-based personalization methods yield 14.92% and 1.07% improvements over non-personalized LLMs, respectively. When combining RAG with PEFT, we observe a further improvement of 15.98%, highlighting the effectiveness of their integration in enhancing personalized text generation. Additionally, we identify a positive correlation between the amount of user data available and the effectiveness of PEFT. This finding suggests that RAG is particularly beneficial for cold-start users -- users with limited personal data -- while PEFT performs better when more user-specific data is available.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
