@inproceedings{chen-etal-2022-meta,
title = "Meta-learning via Language Model In-context Tuning",
author = "Chen, Yanda and
Zhong, Ruiqi and
Zha, Sheng and
Karypis, George and
He, He",
editor = "Muresan, Smaranda and
Nakov, Preslav and
Villavicencio, Aline",
booktitle = "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.acl-long.53",
doi = "10.18653/v1/2022.acl-long.53",
pages = "719--730",
abstract = "The goal of meta-learning is to learn to adapt to a new task with only a few labeled examples. Inspired by the recent progress in large language models, we propose $\textit{in-context tuning}$ (ICT), which recasts task adaptation and prediction as a simple sequence prediction problem: to form the input sequence, we concatenate the task instruction, labeled in-context examples, and the target input to predict; to meta-train the model to learn from in-context examples, we fine-tune a pre-trained language model (LM) to predict the target label given the input sequence on a collection of tasks.We benchmark our method on two collections of text classification tasks: LAMA and BinaryClfs. Compared to MAML which adapts the model through gradient descent, our method leverages the inductive bias of pre-trained LMs to perform pattern matching, and outperforms MAML by an absolute 6{\%} average AUC-ROC score on BinaryClfs, gaining more advantage with increasing model size. Compared to non-fine-tuned in-context learning (i.e. prompting a raw LM), in-context tuning meta-trains the model to learn from in-context examples. On BinaryClfs, ICT improves the average AUC-ROC score by an absolute 10{\%}, and reduces the variance due to example ordering by 6x and example choices by 2x.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2022-meta">
<titleInfo>
<title>Meta-learning via Language Model In-context Tuning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yanda</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruiqi</namePart>
<namePart type="family">Zhong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sheng</namePart>
<namePart type="family">Zha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">George</namePart>
<namePart type="family">Karypis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">He</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Smaranda</namePart>
<namePart type="family">Muresan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aline</namePart>
<namePart type="family">Villavicencio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The goal of meta-learning is to learn to adapt to a new task with only a few labeled examples. Inspired by the recent progress in large language models, we propose in-context tuning (ICT), which recasts task adaptation and prediction as a simple sequence prediction problem: to form the input sequence, we concatenate the task instruction, labeled in-context examples, and the target input to predict; to meta-train the model to learn from in-context examples, we fine-tune a pre-trained language model (LM) to predict the target label given the input sequence on a collection of tasks.We benchmark our method on two collections of text classification tasks: LAMA and BinaryClfs. Compared to MAML which adapts the model through gradient descent, our method leverages the inductive bias of pre-trained LMs to perform pattern matching, and outperforms MAML by an absolute 6% average AUC-ROC score on BinaryClfs, gaining more advantage with increasing model size. Compared to non-fine-tuned in-context learning (i.e. prompting a raw LM), in-context tuning meta-trains the model to learn from in-context examples. On BinaryClfs, ICT improves the average AUC-ROC score by an absolute 10%, and reduces the variance due to example ordering by 6x and example choices by 2x.</abstract>
<identifier type="citekey">chen-etal-2022-meta</identifier>
<identifier type="doi">10.18653/v1/2022.acl-long.53</identifier>
<location>
<url>https://aclanthology.org/2022.acl-long.53</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>719</start>
<end>730</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Meta-learning via Language Model In-context Tuning
%A Chen, Yanda
%A Zhong, Ruiqi
%A Zha, Sheng
%A Karypis, George
%A He, He
%Y Muresan, Smaranda
%Y Nakov, Preslav
%Y Villavicencio, Aline
%S Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F chen-etal-2022-meta
%X The goal of meta-learning is to learn to adapt to a new task with only a few labeled examples. Inspired by the recent progress in large language models, we propose in-context tuning (ICT), which recasts task adaptation and prediction as a simple sequence prediction problem: to form the input sequence, we concatenate the task instruction, labeled in-context examples, and the target input to predict; to meta-train the model to learn from in-context examples, we fine-tune a pre-trained language model (LM) to predict the target label given the input sequence on a collection of tasks.We benchmark our method on two collections of text classification tasks: LAMA and BinaryClfs. Compared to MAML which adapts the model through gradient descent, our method leverages the inductive bias of pre-trained LMs to perform pattern matching, and outperforms MAML by an absolute 6% average AUC-ROC score on BinaryClfs, gaining more advantage with increasing model size. Compared to non-fine-tuned in-context learning (i.e. prompting a raw LM), in-context tuning meta-trains the model to learn from in-context examples. On BinaryClfs, ICT improves the average AUC-ROC score by an absolute 10%, and reduces the variance due to example ordering by 6x and example choices by 2x.
%R 10.18653/v1/2022.acl-long.53
%U https://aclanthology.org/2022.acl-long.53
%U https://doi.org/10.18653/v1/2022.acl-long.53
%P 719-730
Markdown (Informal)
[Meta-learning via Language Model In-context Tuning](https://aclanthology.org/2022.acl-long.53) (Chen et al., ACL 2022)
ACL
- Yanda Chen, Ruiqi Zhong, Sheng Zha, George Karypis, and He He. 2022. Meta-learning via Language Model In-context Tuning. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 719–730, Dublin, Ireland. Association for Computational Linguistics.