Comparing Retrieval-Augmentation and Parameter-Efficient Fine-Tuning for Privacy-Preserving Personalization of Large Language Models
Privacy-preserving methods for personalizing large language models (LLMs) are relatively under-explored. There are two schools of thought on this topic: (1) generating personalized outputs by personalizing the input prompt through retrieval augmentation from the user's personal information (RAG-based methods), and (2) parameter-efficient fine-tuning of LLMs per user that considers efficiency and space limitations (PEFT-based methods). This paper presents the first systematic comparison between two approaches on a wide range of personalization tasks using seven diverse datasets. Our results indicate that RAG-based and PEFT-based personalization methods on average yield 14.92% and 1.07% improvements over the non-personalized LLM, respectively. We find that combining RAG with PEFT elevates these improvements to 15.98%. Additionally, we identify a positive correlation between the amount of user data and PEFT's effectiveness, indicating that RAG is a better choice for cold-start users (i.e., user's with limited personal data).
Code (1)
Tasks
parameter-efficient fine-tuningPrivacy PreservingRAGRetrievalMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Robust Few-Shot Vision-Language Model Adaptation
Pretrained VLMs achieve strong performance on downstream tasks when adapted with just a few labeled examples. As the adapted models inevitably encounter out-of-distribution (OOD) test data that deviates from the in-distr…
Language ModelingLanguage ModellingmodelRetrievalFine Tuning vs. Retrieval Augmented Generation for Less Popular Knowledge
Language Models (LMs) memorize a vast amount of factual knowledge, exhibiting strong performance across diverse tasks and domains. However, it has been observed that the performance diminishes when dealing with less-popu…
Data AugmentationQuestion AnsweringRAGRetrieval+1A Comparative Study of DSL Code Generation: Fine-Tuning vs. Optimized Retrieval Augmentation
Natural Language to Code Generation has made significant progress in recent years with the advent of Large Language Models(LLMs). While generation for general-purpose languages like C, C++, and Python has improved signif…
Code GenerationHallucinationRAGRetrieval+1Benchmarking Children's ASR with Supervised and Self-supervised Speech Foundation Models
Speech foundation models (SFMs) have achieved state-of-the-art results for various speech tasks in supervised (e.g. Whisper) or self-supervised systems (e.g. WavLM). However, the performance of SFMs for child ASR has not…
BenchmarkingData AugmentationAR-RAG: Autoregressive Retrieval Augmentation for Image Generation
We introduce Autoregressive Retrieval Augmentation (AR-RAG), a novel paradigm that enhances image generation by autoregressively incorporating knearest neighbor retrievals at the patch level. Unlike prior methods that pe…
Image Generationparameter-efficient fine-tuningRAGRetrieval