In-Context Retrieval-Augmented Language Models

Ori Ram, Yoav Levine, Itay Dalmedigos, Dor Muhlgay, Amnon Shashua, Kevin Leyton-Brown, Yoav Shoham

Research output: Contribution to journalArticlepeer-review

7 Scopus citations


Retrieval-Augmented Language Modeling (RALM) methods, which condition a language model (LM) on relevant documents from a grounding corpus during generation, were shown to significantly improve language modeling performance. In addition, they can mitigate the problem of factually inac-curate text generation and provide natural source attribution mechanism. Existing RALM approaches focus on modifying the LM architecture in order to facilitate the incorporation of external information, significantly complicating deployment. This paper considers a simple alternative, which we dub In-Context RALM: leaving the LM architecture unchanged and prepending grounding documents to the input, without any further training of the LM. We show that In-Context RALM that builds on off-the-shelf general purpose retrievers provides surpris-ingly large LM gains across model sizes and diverse corpora. We also demonstrate that the document retrieval and ranking mechanism can be specialized to the RALM setting to further boost performance. We conclude that In-Context RALM has considerable potential to increase the prevalence of LM grounding, particularly in settings where a pretrained LM must be used without modification or even via API access.1.

Original languageAmerican English
Pages (from-to)1316-1331
Number of pages16
JournalTransactions of the Association for Computational Linguistics
StatePublished - 2023
Externally publishedYes

Bibliographical note

Publisher Copyright:
© 2023, MIT Press Journals. All rights reserved.


Dive into the research topics of 'In-Context Retrieval-Augmented Language Models'. Together they form a unique fingerprint.

Cite this