Retrieval-augmented Generation

Retrieval-Augmented Generation is a machine learning framework that integrates external knowledge retrieval with text generation by conditioning the generation process on retrieved documents to improve the factual accuracy and relevance of generated responses.

197

Publications

15.3K

Citations

1K

Authors

272

Institutions

Publications per year

2017–2026

196

Authors

1K

  1. FF
    Frank F. Xu

    Stevens Institute of Technology, United States

    4 publications · 379 citations

    4

    h-index

  2. DS
    Daniel Shu Wei Ting

    Singapore National Eye Center, Singapore

    4 publications · 235 citations

    4

    h-index

  3. ZJ
    Zhengbao Jiang

    Carnegie Mellon University, United States

    4 publications · 379 citations

    4

    h-index

  4. GN
    Graham Neubig

    Carnegie Mellon University, United States

    4 publications · 379 citations

    4

    h-index

  5. JC
    Jasmine Chiat Ling Ong

    Singapore General Hospital, Singapore

    4 publications · 235 citations

    4

    h-index

1–5 of 1K

Venues

  1. arXiv (Cornell University)

    Repository · 55 publications · 5.8K citations

    25

    h-index

  2. npj Digital Medicine

    5 publications · 495 citations

    5

    h-index

  3. medRxiv

    Repository · 5 publications · 168 citations

    5

    h-index

  4. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 5 publications · 514 citations

    4

    h-index

  5. Research Square

    Repository · 4 publications · 73 citations

    4

    h-index

1–5