@inproceedings{micheli-fleuret-2021-language,
title = "Language Models are Few-Shot Butlers",
author = "Micheli, Vincent and
Fleuret, Francois",
editor = "Moens, Marie-Francine and
Huang, Xuanjing and
Specia, Lucia and
Yih, Scott Wen-tau",
booktitle = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2021",
address = "Online and Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.emnlp-main.734/",
doi = "10.18653/v1/2021.emnlp-main.734",
pages = "9312--9318",
abstract = "Pretrained language models demonstrate strong performance in most NLP tasks when fine-tuned on small task-specific datasets. Hence, these autoregressive models constitute ideal agents to operate in text-based environments where language understanding and generative capabilities are essential. Nonetheless, collecting expert demonstrations in such environments is a time-consuming endeavour. We introduce a two-stage procedure to learn from a small set of demonstrations and further improve by interacting with an environment. We show that language models fine-tuned with only 1.2{\%} of the expert demonstrations and a simple reinforcement learning algorithm achieve a 51{\%} absolute improvement in success rate over existing methods in the ALFWorld environment."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="micheli-fleuret-2021-language">
<titleInfo>
<title>Language Models are Few-Shot Butlers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vincent</namePart>
<namePart type="family">Micheli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francois</namePart>
<namePart type="family">Fleuret</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marie-Francine</namePart>
<namePart type="family">Moens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuanjing</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Specia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Scott</namePart>
<namePart type="given">Wen-tau</namePart>
<namePart type="family">Yih</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online and Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Pretrained language models demonstrate strong performance in most NLP tasks when fine-tuned on small task-specific datasets. Hence, these autoregressive models constitute ideal agents to operate in text-based environments where language understanding and generative capabilities are essential. Nonetheless, collecting expert demonstrations in such environments is a time-consuming endeavour. We introduce a two-stage procedure to learn from a small set of demonstrations and further improve by interacting with an environment. We show that language models fine-tuned with only 1.2% of the expert demonstrations and a simple reinforcement learning algorithm achieve a 51% absolute improvement in success rate over existing methods in the ALFWorld environment.</abstract>
<identifier type="citekey">micheli-fleuret-2021-language</identifier>
<identifier type="doi">10.18653/v1/2021.emnlp-main.734</identifier>
<location>
<url>https://aclanthology.org/2021.emnlp-main.734/</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>9312</start>
<end>9318</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Language Models are Few-Shot Butlers
%A Micheli, Vincent
%A Fleuret, Francois
%Y Moens, Marie-Francine
%Y Huang, Xuanjing
%Y Specia, Lucia
%Y Yih, Scott Wen-tau
%S Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
%D 2021
%8 November
%I Association for Computational Linguistics
%C Online and Punta Cana, Dominican Republic
%F micheli-fleuret-2021-language
%X Pretrained language models demonstrate strong performance in most NLP tasks when fine-tuned on small task-specific datasets. Hence, these autoregressive models constitute ideal agents to operate in text-based environments where language understanding and generative capabilities are essential. Nonetheless, collecting expert demonstrations in such environments is a time-consuming endeavour. We introduce a two-stage procedure to learn from a small set of demonstrations and further improve by interacting with an environment. We show that language models fine-tuned with only 1.2% of the expert demonstrations and a simple reinforcement learning algorithm achieve a 51% absolute improvement in success rate over existing methods in the ALFWorld environment.
%R 10.18653/v1/2021.emnlp-main.734
%U https://aclanthology.org/2021.emnlp-main.734/
%U https://doi.org/10.18653/v1/2021.emnlp-main.734
%P 9312-9318
Markdown (Informal)
[Language Models are Few-Shot Butlers](https://aclanthology.org/2021.emnlp-main.734/) (Micheli & Fleuret, EMNLP 2021)
ACL
- Vincent Micheli and Francois Fleuret. 2021. Language Models are Few-Shot Butlers. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 9312–9318, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.