@inproceedings{koksal-etal-2023-meal,
title = "{MEAL}: Stable and Active Learning for Few-Shot Prompting",
author = {K{\"o}ksal, Abdullatif and
Schick, Timo and
Schuetze, Hinrich},
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-emnlp.36",
doi = "10.18653/v1/2023.findings-emnlp.36",
pages = "506--517",
abstract = "Few-shot classification has made great strides due to foundation models that, through priming and prompting, are highly effective few-shot learners. However, this approach has high variance both across different sets of few shots (*data selection*) and across different finetuning runs (*run variability*). This is problematic not only because it impedes the fair comparison of different approaches, but especially because it makes few-shot learning too unreliable for many real-world applications. To alleviate these issues, we make two contributions for more stable and effective few-shot learning: First, we propose novel ensembling methods and show that they substantially reduce *run variability*. Second, we introduce a new active learning (AL) criterion for *data selection* and present the first AL-based approach specifically tailored towards prompt-based learning. In our experiments, we show that our combined method, MEAL (**M**ultiprompt finetuning and prediction **E**nsembling with **A**ctive **L**earning), improves overall performance of prompt-based finetuning by 2.3 points on five diverse tasks. We publicly share our code and data splits in https://github.com/akoksal/MEAL.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="koksal-etal-2023-meal">
<titleInfo>
<title>MEAL: Stable and Active Learning for Few-Shot Prompting</title>
</titleInfo>
<name type="personal">
<namePart type="given">Abdullatif</namePart>
<namePart type="family">Köksal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Timo</namePart>
<namePart type="family">Schick</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hinrich</namePart>
<namePart type="family">Schuetze</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Pino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Few-shot classification has made great strides due to foundation models that, through priming and prompting, are highly effective few-shot learners. However, this approach has high variance both across different sets of few shots (*data selection*) and across different finetuning runs (*run variability*). This is problematic not only because it impedes the fair comparison of different approaches, but especially because it makes few-shot learning too unreliable for many real-world applications. To alleviate these issues, we make two contributions for more stable and effective few-shot learning: First, we propose novel ensembling methods and show that they substantially reduce *run variability*. Second, we introduce a new active learning (AL) criterion for *data selection* and present the first AL-based approach specifically tailored towards prompt-based learning. In our experiments, we show that our combined method, MEAL (**M**ultiprompt finetuning and prediction **E**nsembling with **A**ctive **L**earning), improves overall performance of prompt-based finetuning by 2.3 points on five diverse tasks. We publicly share our code and data splits in https://github.com/akoksal/MEAL.</abstract>
<identifier type="citekey">koksal-etal-2023-meal</identifier>
<identifier type="doi">10.18653/v1/2023.findings-emnlp.36</identifier>
<location>
<url>https://aclanthology.org/2023.findings-emnlp.36</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>506</start>
<end>517</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MEAL: Stable and Active Learning for Few-Shot Prompting
%A Köksal, Abdullatif
%A Schick, Timo
%A Schuetze, Hinrich
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Findings of the Association for Computational Linguistics: EMNLP 2023
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F koksal-etal-2023-meal
%X Few-shot classification has made great strides due to foundation models that, through priming and prompting, are highly effective few-shot learners. However, this approach has high variance both across different sets of few shots (*data selection*) and across different finetuning runs (*run variability*). This is problematic not only because it impedes the fair comparison of different approaches, but especially because it makes few-shot learning too unreliable for many real-world applications. To alleviate these issues, we make two contributions for more stable and effective few-shot learning: First, we propose novel ensembling methods and show that they substantially reduce *run variability*. Second, we introduce a new active learning (AL) criterion for *data selection* and present the first AL-based approach specifically tailored towards prompt-based learning. In our experiments, we show that our combined method, MEAL (**M**ultiprompt finetuning and prediction **E**nsembling with **A**ctive **L**earning), improves overall performance of prompt-based finetuning by 2.3 points on five diverse tasks. We publicly share our code and data splits in https://github.com/akoksal/MEAL.
%R 10.18653/v1/2023.findings-emnlp.36
%U https://aclanthology.org/2023.findings-emnlp.36
%U https://doi.org/10.18653/v1/2023.findings-emnlp.36
%P 506-517
Markdown (Informal)
[MEAL: Stable and Active Learning for Few-Shot Prompting](https://aclanthology.org/2023.findings-emnlp.36) (Köksal et al., Findings 2023)
ACL