RESEARCH AUTHOR

Sebastian Riedel

Sebastian Riedel is a credited coauthor of “Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks”. Explore the papers, research findings, and collaborators represented in this collection.

Information retrieval

Papers & publications

1 in this collection

Read the original papers, explore an overview, and collect ideas for your own research.

Open access2020arXiv

Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks

Patrick Lewis, Ethan Perez, Aleksandra Piktus +9 authors

In a nutshellRAG combines a language model with a searchable collection of documents. Retrieved passages give the generator access to external knowledge when producing an answer.

Information retrieval

Read & chat

EXPLORE THE WORK

Research in focus

Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks

A dense retriever selects passages from Wikipedia and a sequence-to-sequence model generates responses conditioned on those passages.

Retrieval and generation can be combined in a trainable system.
An external document index complements knowledge stored in model parameters.
The approach is evaluated on knowledge-intensive language tasks.

Reading context: The quality of an answer depends on both retrieval and generation. Access to relevant passages does not guarantee a correct or fully supported response.

Read the original on arXiv ↗