@inproceedings{samuel-etal-2024-room,
title = "More room for language: Investigating the effect of retrieval on language models",
author = "Samuel, David and
Charpentier, Lucas and
Wold, Sondre",
editor = "Duh, Kevin and
Gomez, Helena and
Bethard, Steven",
booktitle = "Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 2: Short Papers)",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.naacl-short.26",
doi = "10.18653/v1/2024.naacl-short.26",
pages = "282--305",
abstract = "Retrieval-augmented language models pose a promising alternative to standard language modeling. During pretraining, these models search in a corpus of documents for contextually relevant information that could aid the language modeling objective. We introduce an {`}ideal retrieval{'} methodology to study these models in a fully controllable setting. We conduct an extensive evaluation to examine how retrieval augmentation affects the behavior of the underlying language model. Among other things, we observe that these models: (i) save substantially less world knowledge in their weights, (ii) are better at understanding local context and inter-word dependencies, but (iii) are worse at comprehending global context.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="samuel-etal-2024-room">
<titleInfo>
<title>More room for language: Investigating the effect of retrieval on language models</title>
</titleInfo>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Samuel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucas</namePart>
<namePart type="family">Charpentier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sondre</namePart>
<namePart type="family">Wold</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 2: Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Duh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helena</namePart>
<namePart type="family">Gomez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Retrieval-augmented language models pose a promising alternative to standard language modeling. During pretraining, these models search in a corpus of documents for contextually relevant information that could aid the language modeling objective. We introduce an ‘ideal retrieval’ methodology to study these models in a fully controllable setting. We conduct an extensive evaluation to examine how retrieval augmentation affects the behavior of the underlying language model. Among other things, we observe that these models: (i) save substantially less world knowledge in their weights, (ii) are better at understanding local context and inter-word dependencies, but (iii) are worse at comprehending global context.</abstract>
<identifier type="citekey">samuel-etal-2024-room</identifier>
<identifier type="doi">10.18653/v1/2024.naacl-short.26</identifier>
<location>
<url>https://aclanthology.org/2024.naacl-short.26</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>282</start>
<end>305</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T More room for language: Investigating the effect of retrieval on language models
%A Samuel, David
%A Charpentier, Lucas
%A Wold, Sondre
%Y Duh, Kevin
%Y Gomez, Helena
%Y Bethard, Steven
%S Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 2: Short Papers)
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F samuel-etal-2024-room
%X Retrieval-augmented language models pose a promising alternative to standard language modeling. During pretraining, these models search in a corpus of documents for contextually relevant information that could aid the language modeling objective. We introduce an ‘ideal retrieval’ methodology to study these models in a fully controllable setting. We conduct an extensive evaluation to examine how retrieval augmentation affects the behavior of the underlying language model. Among other things, we observe that these models: (i) save substantially less world knowledge in their weights, (ii) are better at understanding local context and inter-word dependencies, but (iii) are worse at comprehending global context.
%R 10.18653/v1/2024.naacl-short.26
%U https://aclanthology.org/2024.naacl-short.26
%U https://doi.org/10.18653/v1/2024.naacl-short.26
%P 282-305
Markdown (Informal)
[More room for language: Investigating the effect of retrieval on language models](https://aclanthology.org/2024.naacl-short.26) (Samuel et al., NAACL 2024)
ACL