paper-with-me

Papers

Comparing Retrieval-Augmentation and Parameter-Efficient Fine-Tuning for Privacy-Preserving Personalization of Large Language Models

2024-09-14 · Alireza Salemi, Hamed Zamani

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).

📄 PDF Abstract BibTeX arXiv:2409.09510

Code (1)

lamp-benchmark/lamp 공식 구현 pytorch

Tasks

parameter-efficient fine-tuningPrivacy PreservingRAGRetrieval

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Attention 설명 없음
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
WordPiece 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…

Similar Papers 제목 키워드 기반

Robust Few-Shot Vision-Language Model Adaptation

2025-06-05 · Hanxin Wang, Tian Liu, Shu Kong

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 ModellingmodelRetrieval

Fine Tuning vs. Retrieval Augmented Generation for Less Popular Knowledge

2024-03-03 · Heydar Soudani, Evangelos Kanoulas, Faegheh Hasibi

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+1

A Comparative Study of DSL Code Generation: Fine-Tuning vs. Optimized Retrieval Augmentation

2024-07-03 · Nastaran Bassamzadeh, Chhaya Methani

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+1

Benchmarking Children's ASR with Supervised and Self-supervised Speech Foundation Models

2024-06-15 · Ruchao Fan, Natarajan Balaji Shankar, Abeer Alwan

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 Augmentation

AR-RAG: Autoregressive Retrieval Augmentation for Image Generation

2025-06-08 · Jingyuan Qi, Zhiyang Xu, Qifan Wang, Lifu Huang

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