paper-with-me

홈 › Papers

Retrieval-Augmented Mixture of LoRA Experts for Uploadable Machine Learning

2024-06-24 · Ziyu Zhao, Leilei Gan, Guoyin Wang, Yuwei Hu, Tao Shen, Hongxia Yang, Kun Kuang, Fei Wu

Low-Rank Adaptation (LoRA) offers an efficient way to fine-tune large language models (LLMs). Its modular and plug-and-play nature allows the integration of various domain-specific LoRAs, enhancing LLM capabilities. Open-source platforms like Huggingface and Modelscope have introduced a new computational paradigm, Uploadable Machine Learning (UML). In UML, contributors use decentralized data to train specialized adapters, which are then uploaded to a central platform to improve LLMs. This platform uses these domain-specific adapters to handle mixed-task requests requiring personalized service. Previous research on LoRA composition either focuses on specific tasks or fixes the LoRA selection during training. However, in UML, the pool of LoRAs is dynamically updated with new uploads, requiring a generalizable selection mechanism for unseen LoRAs. Additionally, the mixed-task nature of downstream requests necessitates personalized services. To address these challenges, we propose Retrieval-Augmented Mixture of LoRA Experts (RAMoLE), a framework that adaptively retrieves and composes multiple LoRAs based on input prompts. RAMoLE has three main components: LoraRetriever for identifying and retrieving relevant LoRAs, an on-the-fly MoLE mechanism for coordinating the retrieved LoRAs, and efficient batch inference for handling heterogeneous requests. Experimental results show that RAMoLE consistently outperforms baselines, highlighting its effectiveness and scalability.

📄 PDF Abstract BibTeX arXiv:2406.16989

Code (0)

등록된 구현이 없습니다.

Tasks

Retrieval

Methods 이 논문이 사용한 방법론

Golden Queue Managers 설명 없음

Similar Papers 제목 키워드 기반

MixLoRA-DSI: Dynamically Expandable Mixture-of-LoRA Experts for Rehearsal-Free Generative Retrieval over Dynamic Corpora

2025-07-14 · Tuan-Luc Huynh, Thuy-Trang Vu, Weiqing Wang, Trung Le 외 arxiv

Continually updating model-based indexes in generative retrieval with new documents remains challenging, as full retraining is computationally expensive and impractical under resource constraints. We propose MixLoRA-DSI,…

A Simple Architecture for Enterprise Large Language Model Applications based on Role based security and Clearance Levels using Retrieval-Augmented Generation or Mixture of Experts

2024-07-09 · Atilla Özgür, Yılmaz Uygun

This study proposes a simple architecture for Enterprise application for Large Language Models (LLMs) for role based security and NATO clearance levels. Our proposal aims to address the limitations of current LLMs in han…

Language ModelingLanguage ModellingLarge Language ModelMixture-of-Experts+3

MoG: Mixture of Experts for Graph-based Retrieval-Augmented Generation

2026-05-29 · Zheng Yuan, Chuang Zhou, Linhao Luo, Siyu An 외 arxiv

Retrieval-augmented generation is intensively studied to ground large language models on external evidence. However, retrieving from a unified knowledge base could inevitably introduce irrelevant information that may mis…

Multimodal Mixture-of-Experts with Retrieval Augmentation for Protein Active Site Identification

2026-03-02 · Jiayang Wu, Jiale Zhou, Rubo Wang, Xingyi Zhang 외 arxiv

Accurate identification of protein active sites at the residue level is crucial for understanding protein function and advancing drug discovery. However, current methods face two critical challenges: vulnerability in sin…

Drug Discovery

LoRA-Augmented Generation (LAG) for Knowledge-Intensive Language Tasks

2025-07-07 · William Fleshman, Benjamin Van Durme arxiv

The proliferation of fine-tuned language model experts for specific tasks and domains signals the need for efficient selection and combination methods. We propose LoRA-Augmented Generation (LAG) for leveraging large libr…