@inproceedings{park-etal-2022-lm,
title = "{LM}-{BFF}-{MS}: Improving Few-Shot Fine-tuning of Language Models based on Multiple Soft Demonstration Memory",
author = "Park, Eunhwan and
Jeon, Donghyeon and
Kim, Seonhoon and
Kang, Inho and
Na, Seung-Hoon",
editor = "Muresan, Smaranda and
Nakov, Preslav and
Villavicencio, Aline",
booktitle = "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.acl-short.34/",
doi = "10.18653/v1/2022.acl-short.34",
pages = "310--317",
abstract = "LM-BFF (CITATION) achieves significant few-shot performance by using auto-generated prompts and adding demonstrations similar to an input example. To improve the approach of LM-BFF, this paper proposes \textbf{LM-BFF-MS}{---}\textbf{b}etter \textbf{f}ew-shot \textbf{f}ine-tuning of \textbf{l}anguage \textbf{m}odels with \textbf{m}ultiple \textbf{s}oft demonstrations by making its further extensions, which include 1) prompts with \textit{multiple demonstrations} based on automatic generation of multiple label words; and 2) \textit{soft demonstration memory} which consists of multiple sequences of \textit{globally shared} word embeddings for a similar context. Experiments conducted on eight NLP tasks show that LM-BFF-MS leads to improvements over LM-BFF on five tasks, particularly achieving 94.0 and 90.4 on SST-2 and MRPC, respectively."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="park-etal-2022-lm">
<titleInfo>
<title>LM-BFF-MS: Improving Few-Shot Fine-tuning of Language Models based on Multiple Soft Demonstration Memory</title>
</titleInfo>
<name type="personal">
<namePart type="given">Eunhwan</namePart>
<namePart type="family">Park</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Donghyeon</namePart>
<namePart type="family">Jeon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seonhoon</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Inho</namePart>
<namePart type="family">Kang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seung-Hoon</namePart>
<namePart type="family">Na</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 2: Short 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>LM-BFF (CITATION) achieves significant few-shot performance by using auto-generated prompts and adding demonstrations similar to an input example. To improve the approach of LM-BFF, this paper proposes LM-BFF-MS—better few-shot fine-tuning of language models with multiple soft demonstrations by making its further extensions, which include 1) prompts with multiple demonstrations based on automatic generation of multiple label words; and 2) soft demonstration memory which consists of multiple sequences of globally shared word embeddings for a similar context. Experiments conducted on eight NLP tasks show that LM-BFF-MS leads to improvements over LM-BFF on five tasks, particularly achieving 94.0 and 90.4 on SST-2 and MRPC, respectively.</abstract>
<identifier type="citekey">park-etal-2022-lm</identifier>
<identifier type="doi">10.18653/v1/2022.acl-short.34</identifier>
<location>
<url>https://aclanthology.org/2022.acl-short.34/</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>310</start>
<end>317</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T LM-BFF-MS: Improving Few-Shot Fine-tuning of Language Models based on Multiple Soft Demonstration Memory
%A Park, Eunhwan
%A Jeon, Donghyeon
%A Kim, Seonhoon
%A Kang, Inho
%A Na, Seung-Hoon
%Y Muresan, Smaranda
%Y Nakov, Preslav
%Y Villavicencio, Aline
%S Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F park-etal-2022-lm
%X LM-BFF (CITATION) achieves significant few-shot performance by using auto-generated prompts and adding demonstrations similar to an input example. To improve the approach of LM-BFF, this paper proposes LM-BFF-MS—better few-shot fine-tuning of language models with multiple soft demonstrations by making its further extensions, which include 1) prompts with multiple demonstrations based on automatic generation of multiple label words; and 2) soft demonstration memory which consists of multiple sequences of globally shared word embeddings for a similar context. Experiments conducted on eight NLP tasks show that LM-BFF-MS leads to improvements over LM-BFF on five tasks, particularly achieving 94.0 and 90.4 on SST-2 and MRPC, respectively.
%R 10.18653/v1/2022.acl-short.34
%U https://aclanthology.org/2022.acl-short.34/
%U https://doi.org/10.18653/v1/2022.acl-short.34
%P 310-317
Markdown (Informal)
[LM-BFF-MS: Improving Few-Shot Fine-tuning of Language Models based on Multiple Soft Demonstration Memory](https://aclanthology.org/2022.acl-short.34/) (Park et al., ACL 2022)
- LM-BFF-MS: Improving Few-Shot Fine-tuning of Language Models based on Multiple Soft Demonstration Memory (Park et al., ACL 2022)
ACL
- Eunhwan Park, Donghyeon Jeon, Seonhoon Kim, Inho Kang, and Seung-Hoon Na. 2022. LM-BFF-MS: Improving Few-Shot Fine-tuning of Language Models based on Multiple Soft Demonstration Memory. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 310–317, Dublin, Ireland. Association for Computational Linguistics.