<ul><li>CoRAG is a framework that extends Retrieval-Augmented Generation (RAG) models to collaborative settings.</li><li>CoRAG allows clients to jointly train a shared model using a collaborative passage store.</li><li>CoRAG outperforms parametric collaborative learning methods and locally trained RAG models in low-resource scenarios.</li><li>The trade-off between leveraging a collectively enriched knowledge base and the potential risk of incorporating detrimental passages is a key consideration in collaborative RAG.</li></ul>

CoRAG: Collaborative Retrieval-Augmented Generation

Discover more