@inproceedings{xu-etal-2022-gps,
title = "{GPS}: Genetic Prompt Search for Efficient Few-Shot Learning",
author = "Xu, Hanwei and
Chen, Yujun and
Du, Yulun and
Shao, Nan and
Yanggang, Wang and
Li, Haiyu and
Yang, Zhilin",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.emnlp-main.559",
doi = "10.18653/v1/2022.emnlp-main.559",
pages = "8162--8171",
abstract = "Prompt-based techniques have demostrated great potential for improving the few-shot generalization of pretrained language models. However, their performance heavily relies on the manual design of prompts and thus requiring a lot of human efforts. In this paper, we introduce Genetic Prompt Search (GPS) to improve few-shot learning with prompts, which utilizes a genetic algorithm to automatically search for the best prompt.GPS is gradient-free and requires no update of model parameters but only a small validation set. Experiments on diverse datasets proved the effectiveness of GPS, which outperforms manual prompts by a large margin of 2.6 points. Our method is also better than other parameter-efficient tuning methods such as prompt tuning.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xu-etal-2022-gps">
<titleInfo>
<title>GPS: Genetic Prompt Search for Efficient Few-Shot Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hanwei</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yujun</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulun</namePart>
<namePart type="family">Du</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nan</namePart>
<namePart type="family">Shao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wang</namePart>
<namePart type="family">Yanggang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haiyu</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhilin</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yoav</namePart>
<namePart type="family">Goldberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zornitsa</namePart>
<namePart type="family">Kozareva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Prompt-based techniques have demostrated great potential for improving the few-shot generalization of pretrained language models. However, their performance heavily relies on the manual design of prompts and thus requiring a lot of human efforts. In this paper, we introduce Genetic Prompt Search (GPS) to improve few-shot learning with prompts, which utilizes a genetic algorithm to automatically search for the best prompt.GPS is gradient-free and requires no update of model parameters but only a small validation set. Experiments on diverse datasets proved the effectiveness of GPS, which outperforms manual prompts by a large margin of 2.6 points. Our method is also better than other parameter-efficient tuning methods such as prompt tuning.</abstract>
<identifier type="citekey">xu-etal-2022-gps</identifier>
<identifier type="doi">10.18653/v1/2022.emnlp-main.559</identifier>
<location>
<url>https://aclanthology.org/2022.emnlp-main.559</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>8162</start>
<end>8171</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T GPS: Genetic Prompt Search for Efficient Few-Shot Learning
%A Xu, Hanwei
%A Chen, Yujun
%A Du, Yulun
%A Shao, Nan
%A Yanggang, Wang
%A Li, Haiyu
%A Yang, Zhilin
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F xu-etal-2022-gps
%X Prompt-based techniques have demostrated great potential for improving the few-shot generalization of pretrained language models. However, their performance heavily relies on the manual design of prompts and thus requiring a lot of human efforts. In this paper, we introduce Genetic Prompt Search (GPS) to improve few-shot learning with prompts, which utilizes a genetic algorithm to automatically search for the best prompt.GPS is gradient-free and requires no update of model parameters but only a small validation set. Experiments on diverse datasets proved the effectiveness of GPS, which outperforms manual prompts by a large margin of 2.6 points. Our method is also better than other parameter-efficient tuning methods such as prompt tuning.
%R 10.18653/v1/2022.emnlp-main.559
%U https://aclanthology.org/2022.emnlp-main.559
%U https://doi.org/10.18653/v1/2022.emnlp-main.559
%P 8162-8171
Markdown (Informal)
[GPS: Genetic Prompt Search for Efficient Few-Shot Learning](https://aclanthology.org/2022.emnlp-main.559) (Xu et al., EMNLP 2022)
ACL
- Hanwei Xu, Yujun Chen, Yulun Du, Nan Shao, Wang Yanggang, Haiyu Li, and Zhilin Yang. 2022. GPS: Genetic Prompt Search for Efficient Few-Shot Learning. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 8162–8171, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.