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 “2.4 Training” · whole deck
2.4 Training
- How is RAG trained, and what stays fixed?By minimizing the negative marginal log-likelihood \(-\sum_j \log p(y_j \mid x_j)\) with Adam, with no supervision on which document to retrieve. Only the query encoder and BART are fine-tuned; the document encoder and index stay fixed, avoiding costly re-indexing (unlike REALM), without hurting performance.
- Lewis et al., 2020, Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks (Advances in Neural Information Processing Systems 33 (NeurIPS 2020)), §2.4
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