Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
At a glance
RAG finds relevant documents to help a language model generate better-informed answers.
In one paragraph
Introduced retrieval-augmented generation (RAG), combining a language model with a system that finds relevant documents before generating an answer. Using Wikipedia as an external knowledge source improved question answering and produced more factual text than a model relying only on its training.
Authors 12
- Patrick Lewis
- Ethan Perez
- Aleksandra Piktus
- Fabio Petroni
- Vladimir Karpukhin
- Naman Goyal
- Heinrich Küttler
- Mike Lewis
- Wen-tau Yih
- Tim Rocktäschel
- Sebastian Riedel
- Douwe Kiela
