@inproceedings{chen-etal-2023-exploring,
title = "Exploring Lottery Prompts for Pre-trained Language Models",
author = "Chen, Yulin and
Ding, Ning and
Wang, Xiaobin and
Hu, Shengding and
Zheng, Haitao and
Liu, Zhiyuan and
Xie, Pengjun",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.acl-long.860",
doi = "10.18653/v1/2023.acl-long.860",
pages = "15428--15444",
abstract = "Consistently scaling pre-trained language models (PLMs) imposes substantial burdens on model adaptation, necessitating more efficient alternatives to conventional fine-tuning. Given the advantage of prompting in the zero-shot setting and the observed performance fluctuation among different prompts, we explore the instance-level prompt and their generalizability.By searching through the prompt space, we first validate the assumption that for every instance, there is almost always a lottery prompt that induces the correct prediction from the PLM, and such prompt can be obtained at a low cost thanks to the inherent ability of PLMs.Meanwhile, it is shown that some strong lottery prompts have high performance over the whole training set, and they are equipped with distinguishable linguistic features. Lastly, we attempt to generalize the searched strong lottery prompts to unseen data with prompt ensembling method. Experiments are conducted on various types of NLP classification tasks and demonstrate that the proposed method can achieve comparable results with other gradient-free and optimization-free baselines.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2023-exploring">
<titleInfo>
<title>Exploring Lottery Prompts for Pre-trained Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yulin</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ning</namePart>
<namePart type="family">Ding</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaobin</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shengding</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haitao</namePart>
<namePart type="family">Zheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhiyuan</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pengjun</namePart>
<namePart type="family">Xie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Consistently scaling pre-trained language models (PLMs) imposes substantial burdens on model adaptation, necessitating more efficient alternatives to conventional fine-tuning. Given the advantage of prompting in the zero-shot setting and the observed performance fluctuation among different prompts, we explore the instance-level prompt and their generalizability.By searching through the prompt space, we first validate the assumption that for every instance, there is almost always a lottery prompt that induces the correct prediction from the PLM, and such prompt can be obtained at a low cost thanks to the inherent ability of PLMs.Meanwhile, it is shown that some strong lottery prompts have high performance over the whole training set, and they are equipped with distinguishable linguistic features. Lastly, we attempt to generalize the searched strong lottery prompts to unseen data with prompt ensembling method. Experiments are conducted on various types of NLP classification tasks and demonstrate that the proposed method can achieve comparable results with other gradient-free and optimization-free baselines.</abstract>
<identifier type="citekey">chen-etal-2023-exploring</identifier>
<identifier type="doi">10.18653/v1/2023.acl-long.860</identifier>
<location>
<url>https://aclanthology.org/2023.acl-long.860</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>15428</start>
<end>15444</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Exploring Lottery Prompts for Pre-trained Language Models
%A Chen, Yulin
%A Ding, Ning
%A Wang, Xiaobin
%A Hu, Shengding
%A Zheng, Haitao
%A Liu, Zhiyuan
%A Xie, Pengjun
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F chen-etal-2023-exploring
%X Consistently scaling pre-trained language models (PLMs) imposes substantial burdens on model adaptation, necessitating more efficient alternatives to conventional fine-tuning. Given the advantage of prompting in the zero-shot setting and the observed performance fluctuation among different prompts, we explore the instance-level prompt and their generalizability.By searching through the prompt space, we first validate the assumption that for every instance, there is almost always a lottery prompt that induces the correct prediction from the PLM, and such prompt can be obtained at a low cost thanks to the inherent ability of PLMs.Meanwhile, it is shown that some strong lottery prompts have high performance over the whole training set, and they are equipped with distinguishable linguistic features. Lastly, we attempt to generalize the searched strong lottery prompts to unseen data with prompt ensembling method. Experiments are conducted on various types of NLP classification tasks and demonstrate that the proposed method can achieve comparable results with other gradient-free and optimization-free baselines.
%R 10.18653/v1/2023.acl-long.860
%U https://aclanthology.org/2023.acl-long.860
%U https://doi.org/10.18653/v1/2023.acl-long.860
%P 15428-15444
Markdown (Informal)
[Exploring Lottery Prompts for Pre-trained Language Models](https://aclanthology.org/2023.acl-long.860) (Chen et al., ACL 2023)
ACL
- Yulin Chen, Ning Ding, Xiaobin Wang, Shengding Hu, Haitao Zheng, Zhiyuan Liu, and Pengjun Xie. 2023. Exploring Lottery Prompts for Pre-trained Language Models. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 15428–15444, Toronto, Canada. Association for Computational Linguistics.