RAG (Retrieval-Augmented Generation)

GPTKB entity

Predicate	Object
gptkbp:instanceOf	machine learning technique natural language processing method
gptkbp:application	open-domain question answering knowledge-intensive tasks
gptkbp:architecture	retrieval-augmented generation
gptkbp:author	gptkb:Mike_Lewis gptkb:Sebastian_Riedel gptkb:Patrick_Lewis gptkb:Douwe_Kiela gptkb:Fabio_Petroni gptkb:Tim_Rocktäschel gptkb:Aleksandra_Piktus gptkb:Ethan_Perez gptkb:Heinrich_Küttler gptkb:Naman_Goyal gptkb:Vladimir_Karpukhin gptkb:Wen-tau_Yih
gptkbp:citation	gptkb:Advances_in_Neural_Information_Processing_Systems_(NeurIPS) gptkb:Retrieval-Augmented_Generation_for_Knowledge-Intensive_NLP_Tasks 2020
gptkbp:combines	generator retrieval
gptkbp:developedBy	gptkb:Facebook_AI_Research
gptkbp:generation	sequence-to-sequence model
gptkbp:generatorModel	gptkb:BART gptkb:T5
https://www.w3.org/2000/01/rdf-schema#label	RAG (Retrieval-Augmented Generation)
gptkbp:improves	factual accuracy knowledge coverage
gptkbp:input	query
gptkbp:introducedIn	2020
gptkbp:notableFor	end-to-end differentiability improved performance on knowledge-intensive tasks retrieval-augmented text generation
gptkbp:openSource	gptkb:Hugging_Face_Transformers
gptkbp:output	generated text
gptkbp:relatedTo	language models knowledge retrieval retriever-reader architecture open-domain QA
gptkbp:retrieverModel	Dense Passage Retriever
gptkbp:retrieverType	dense retriever
gptkbp:uses	external knowledge sources generator model retriever model document index
gptkbp:bfsParent	gptkb:Haystack
gptkbp:bfsLayer	6