@inproceedings{kruszewski-etal-2023-disco,
title = "disco: a toolkit for Distributional Control of Generative Models",
author = "Kruszewski, Germ{\'a}n and
Rozen, Jos and
Dymetman, Marc",
editor = "Bollegala, Danushka and
Huang, Ruihong and
Ritter, Alan",
booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.acl-demo.14",
doi = "10.18653/v1/2023.acl-demo.14",
pages = "144--160",
abstract = "Pre-trained language models and other generative models have revolutionized NLP and beyond. However, these models tend to reproduce undesirable biases present in their training data. Also, they may overlook patterns that are important but challenging to capture. To address these limitations, researchers have introduced distributional control techniques. These techniques, not limited to language, allow controlling the prevalence (i.e. expectations) of any features of interest in the model{'}s outputs. Despite their potential, the widespread adoption of these techniques has been hindered by the difficulty in adapting the complex, disconnected code. Here, we present disco, an open-source Python library that brings these techniques to the broader public",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kruszewski-etal-2023-disco">
<titleInfo>
<title>disco: a toolkit for Distributional Control of Generative Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Germán</namePart>
<namePart type="family">Kruszewski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jos</namePart>
<namePart type="family">Rozen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marc</namePart>
<namePart type="family">Dymetman</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 3: System Demonstrations)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Danushka</namePart>
<namePart type="family">Bollegala</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruihong</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Ritter</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>Pre-trained language models and other generative models have revolutionized NLP and beyond. However, these models tend to reproduce undesirable biases present in their training data. Also, they may overlook patterns that are important but challenging to capture. To address these limitations, researchers have introduced distributional control techniques. These techniques, not limited to language, allow controlling the prevalence (i.e. expectations) of any features of interest in the model’s outputs. Despite their potential, the widespread adoption of these techniques has been hindered by the difficulty in adapting the complex, disconnected code. Here, we present disco, an open-source Python library that brings these techniques to the broader public</abstract>
<identifier type="citekey">kruszewski-etal-2023-disco</identifier>
<identifier type="doi">10.18653/v1/2023.acl-demo.14</identifier>
<location>
<url>https://aclanthology.org/2023.acl-demo.14</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>144</start>
<end>160</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T disco: a toolkit for Distributional Control of Generative Models
%A Kruszewski, Germán
%A Rozen, Jos
%A Dymetman, Marc
%Y Bollegala, Danushka
%Y Huang, Ruihong
%Y Ritter, Alan
%S Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F kruszewski-etal-2023-disco
%X Pre-trained language models and other generative models have revolutionized NLP and beyond. However, these models tend to reproduce undesirable biases present in their training data. Also, they may overlook patterns that are important but challenging to capture. To address these limitations, researchers have introduced distributional control techniques. These techniques, not limited to language, allow controlling the prevalence (i.e. expectations) of any features of interest in the model’s outputs. Despite their potential, the widespread adoption of these techniques has been hindered by the difficulty in adapting the complex, disconnected code. Here, we present disco, an open-source Python library that brings these techniques to the broader public
%R 10.18653/v1/2023.acl-demo.14
%U https://aclanthology.org/2023.acl-demo.14
%U https://doi.org/10.18653/v1/2023.acl-demo.14
%P 144-160
Markdown (Informal)
[disco: a toolkit for Distributional Control of Generative Models](https://aclanthology.org/2023.acl-demo.14) (Kruszewski et al., ACL 2023)
ACL
- Germán Kruszewski, Jos Rozen, and Marc Dymetman. 2023. disco: a toolkit for Distributional Control of Generative Models. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations), pages 144–160, Toronto, Canada. Association for Computational Linguistics.