- Published on
CoRAG: Collaborative Retrieval-Augmented Generation
few-shot-learningcollaborative-passage-storehard-negativesirrelevant-passagesrelevant-passagesRetrieval-Augmented-Generationdesign-challengesfuture-researchbenchmark-for-collaborative-homogeneous-open-domain-question-answeringcollectively-enriched-knowledge-baselow-resource-scenarioscollaborative-settings
Language Technologies Institute, Carnegie Mellon University•Machine Learning Department, Carnegie Mellon University•
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,...