Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
Lewis et al., 2020, Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks (Advances in Neural Information Processing Systems 33 (NeurIPS 2020))
Subscriber deck — free during early access
1 cards in “2.3 Generator: BART” · whole deck
2.3 Generator: BART
- What generator does RAG use, and how does it see retrieved text?BART-large (400M parameters), a denoising-pretrained seq2seq Transformer; the input \(x\) and retrieved passage \(z\) are simply concatenated as its input.
- Lewis et al., 2020, Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks (Advances in Neural Information Processing Systems 33 (NeurIPS 2020)), §2.3
Source
- Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich Küttler, Mike Lewis, Wen-tau Yih, Tim Rocktäschel, Sebastian Riedel and Douwe Kiela. 2020. Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks. In Advances in Neural Information Processing Systems 33 (NeurIPS 2020). https://papers.nips.cc/paper/2020/hash/6b493230205f780e1bc26945df7481e5-Abstract.html