CoRAG: Collaborative Retrieval-Augmented Generation

2025-04-02 · Aashiq Muhamed, Mona Diab, Virginia Smith

Retrieval-Augmented Generation (RAG) models excel in knowledge-intensive tasks, especially under few-shot learning constraints. We introduce CoRAG, a framework extending RAG to collaborative settings, where clients jointly train a shared model using a collaborative passage store. To evaluate CoRAG, we introduce CRAB, a benchmark for collaborative homogeneous open-domain question answering. Our experiments demonstrate that CoRAG consistently outperforms both parametric collaborative learning methods and locally trained RAG models in low-resource scenarios. Further analysis reveals the critical importance of relevant passages within the shared store, the surprising benefits of incorporating irrelevant passages, and the potential for hard negatives to negatively impact performance. This introduces a novel consideration in collaborative RAG: the trade-off between leveraging a collectively enriched knowledge base and the potential risk of incorporating detrimental passages from other clients. Our findings underscore the viability of CoRAG, while also highlighting key design challenges and promising avenues for future research.

📄 PDF Abstract BibTeX arXiv:2504.01883

Code (0)

등록된 구현이 없습니다.

Tasks

Few-Shot Learning Open-Domain Question Answering Question Answering RAG RetrievalRetrieval-augmented Generation

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

Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…

Residual Connection 설명 없음

WordPiece 설명 없음

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.

Adam 설명 없음

Weight Decay 설명 없음

Chain-of-Retrieval Augmented Generation

2025-01-24 · Liang Wang, Haonan Chen, Nan Yang, Xiaolong Huang 외

This paper introduces an approach for training o1-like RAG models that retrieve and reason over relevant information step by step before generating the final answer. Conventional RAG methods usually perform a single retr…

Multi-hop Question Answering Question Answering RAG Retrieval+1

Rethinking Retrieval-Augmented Generation as a Cooperative Decision-Making Problem

2026-02-21 · Lichang Song, Ting Long, Yi Chang arxiv

Retrieval-Augmented Generation (RAG) has demonstrated strong effectiveness in knowledge-intensive tasks by grounding language generation in external evidence. Despite its success, many existing RAG systems are built base…

MedCoRAG: Interpretable Hepatology Diagnosis via Hybrid Evidence Retrieval and Multispecialty Consensus

2026-03-05 · Zheng Li, Jiayi Xu, Zhikai Hu, Hechang Chen 외 arxiv

Diagnosing hepatic diseases accurately and interpretably is critical, yet it remains challenging in real-world clinical settings. Existing AI approaches for clinical diagnosis often lack transparency, structured reasonin…

ECoRAG: Evidentiality-guided Compression for Long Context RAG

2025-06-05 · Yeonseok Jeong, Jinsu Kim, Dohyeon Lee, Seung-won Hwang

Large Language Models (LLMs) have shown remarkable performance in Open-Domain Question Answering (ODQA) by leveraging external documents through Retrieval-Augmented Generation (RAG). To reduce RAG overhead, from longer c…

Answer Generation Open-Domain Question Answering Question Answering RAG+1

CORAG: A Cost-Constrained Retrieval Optimization System for Retrieval-Augmented Generation

2024-11-01 · Ziting Wang, Haitao Yuan, Wei Dong, Gao Cong 외

Large Language Models (LLMs) have demonstrated remarkable generation capabilities but often struggle to access up-to-date information, which can lead to hallucinations. Retrieval-Augmented Generation (RAG) addresses this…

RAG Retrieval Retrieval-augmented Generation