@inproceedings{min-etal-2022-metaicl,
title = "{M}eta{ICL}: Learning to Learn In Context",
author = "Min, Sewon and
Lewis, Mike and
Zettlemoyer, Luke and
Hajishirzi, Hannaneh",
editor = "Carpuat, Marine and
de Marneffe, Marie-Catherine and
Meza Ruiz, Ivan Vladimir",
booktitle = "Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jul,
year = "2022",
address = "Seattle, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.naacl-main.201",
doi = "10.18653/v1/2022.naacl-main.201",
pages = "2791--2809",
abstract = "We introduce MetaICL (Meta-training for In-Context Learning), a new meta-training framework for few-shot learning where a pretrained language model is tuned to do in-context learning on a large set of training tasks. This meta-training enables the model to more effectively learn a new task in context at test time, by simply conditioning on a few training examples with no parameter updates or task-specific templates. We experiment on a large, diverse collection of tasks consisting of 142 NLP datasets including classification, question answering, natural language inference, paraphrase detection and more, across seven different meta-training/target splits. MetaICL outperforms a range of baselines including in-context learning without meta-training and multi-task learning followed by zero-shot transfer. We find that the gains are particularly significant for target tasks that have domain shifts from the meta-training tasks, and that using a diverse set of the meta-training tasks is key to improvements. We also show that MetaICL approaches (and sometimes beats) the performance of models fully finetuned on the target task training data, and outperforms much bigger models with nearly 8x parameters.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="min-etal-2022-metaicl">
<titleInfo>
<title>MetaICL: Learning to Learn In Context</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sewon</namePart>
<namePart type="family">Min</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mike</namePart>
<namePart type="family">Lewis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luke</namePart>
<namePart type="family">Zettlemoyer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hannaneh</namePart>
<namePart type="family">Hajishirzi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marine</namePart>
<namePart type="family">Carpuat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie-Catherine</namePart>
<namePart type="family">de Marneffe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="given">Vladimir</namePart>
<namePart type="family">Meza Ruiz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Seattle, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We introduce MetaICL (Meta-training for In-Context Learning), a new meta-training framework for few-shot learning where a pretrained language model is tuned to do in-context learning on a large set of training tasks. This meta-training enables the model to more effectively learn a new task in context at test time, by simply conditioning on a few training examples with no parameter updates or task-specific templates. We experiment on a large, diverse collection of tasks consisting of 142 NLP datasets including classification, question answering, natural language inference, paraphrase detection and more, across seven different meta-training/target splits. MetaICL outperforms a range of baselines including in-context learning without meta-training and multi-task learning followed by zero-shot transfer. We find that the gains are particularly significant for target tasks that have domain shifts from the meta-training tasks, and that using a diverse set of the meta-training tasks is key to improvements. We also show that MetaICL approaches (and sometimes beats) the performance of models fully finetuned on the target task training data, and outperforms much bigger models with nearly 8x parameters.</abstract>
<identifier type="citekey">min-etal-2022-metaicl</identifier>
<identifier type="doi">10.18653/v1/2022.naacl-main.201</identifier>
<location>
<url>https://aclanthology.org/2022.naacl-main.201</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>2791</start>
<end>2809</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MetaICL: Learning to Learn In Context
%A Min, Sewon
%A Lewis, Mike
%A Zettlemoyer, Luke
%A Hajishirzi, Hannaneh
%Y Carpuat, Marine
%Y de Marneffe, Marie-Catherine
%Y Meza Ruiz, Ivan Vladimir
%S Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
%D 2022
%8 July
%I Association for Computational Linguistics
%C Seattle, United States
%F min-etal-2022-metaicl
%X We introduce MetaICL (Meta-training for In-Context Learning), a new meta-training framework for few-shot learning where a pretrained language model is tuned to do in-context learning on a large set of training tasks. This meta-training enables the model to more effectively learn a new task in context at test time, by simply conditioning on a few training examples with no parameter updates or task-specific templates. We experiment on a large, diverse collection of tasks consisting of 142 NLP datasets including classification, question answering, natural language inference, paraphrase detection and more, across seven different meta-training/target splits. MetaICL outperforms a range of baselines including in-context learning without meta-training and multi-task learning followed by zero-shot transfer. We find that the gains are particularly significant for target tasks that have domain shifts from the meta-training tasks, and that using a diverse set of the meta-training tasks is key to improvements. We also show that MetaICL approaches (and sometimes beats) the performance of models fully finetuned on the target task training data, and outperforms much bigger models with nearly 8x parameters.
%R 10.18653/v1/2022.naacl-main.201
%U https://aclanthology.org/2022.naacl-main.201
%U https://doi.org/10.18653/v1/2022.naacl-main.201
%P 2791-2809
Markdown (Informal)
[MetaICL: Learning to Learn In Context](https://aclanthology.org/2022.naacl-main.201) (Min et al., NAACL 2022)
ACL
- Sewon Min, Mike Lewis, Luke Zettlemoyer, and Hannaneh Hajishirzi. 2022. MetaICL: Learning to Learn In Context. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 2791–2809, Seattle, United States. Association for Computational Linguistics.