@inproceedings{wu-etal-2024-pyvene,
title = "pyvene: A Library for Understanding and Improving {P}y{T}orch Models via Interventions",
author = "Wu, Zhengxuan and
Geiger, Atticus and
Arora, Aryaman and
Huang, Jing and
Wang, Zheng and
Goodman, Noah and
Manning, Christopher and
Potts, Christopher",
editor = "Chang, Kai-Wei and
Lee, Annie and
Rajani, Nazneen",
booktitle = "Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 3: System Demonstrations)",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.naacl-demo.16",
pages = "158--165",
abstract = "Interventions on model-internal states are fundamental operations in many areas of AI, including model editing, steering, robustness, and interpretability. To facilitate such research, we introduce $pyvene$, an open-source Python library that supports customizable interventions on a range of different PyTorch modules. $pyvene$ supports complex intervention schemes with an intuitive configuration format, and its interventions can be static or include trainable parameters. We show how $pyvene$ provides a unified and extensible framework for performing interventions on neural models and sharing the intervened upon models with others. We illustrate the power of the library via interpretability analyses using causal abstraction and knowledge localization. We publish our library through Python Package Index (PyPI) and provide code, documentation, and tutorials at {`}https://github.com/stanfordnlp/pyvene{`}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wu-etal-2024-pyvene">
<titleInfo>
<title>pyvene: A Library for Understanding and Improving PyTorch Models via Interventions</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhengxuan</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Atticus</namePart>
<namePart type="family">Geiger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aryaman</namePart>
<namePart type="family">Arora</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jing</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zheng</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Noah</namePart>
<namePart type="family">Goodman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Manning</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Potts</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 3: System Demonstrations)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kai-Wei</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Annie</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nazneen</namePart>
<namePart type="family">Rajani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Interventions on model-internal states are fundamental operations in many areas of AI, including model editing, steering, robustness, and interpretability. To facilitate such research, we introduce pyvene, an open-source Python library that supports customizable interventions on a range of different PyTorch modules. pyvene supports complex intervention schemes with an intuitive configuration format, and its interventions can be static or include trainable parameters. We show how pyvene provides a unified and extensible framework for performing interventions on neural models and sharing the intervened upon models with others. We illustrate the power of the library via interpretability analyses using causal abstraction and knowledge localization. We publish our library through Python Package Index (PyPI) and provide code, documentation, and tutorials at ‘https://github.com/stanfordnlp/pyvene‘.</abstract>
<identifier type="citekey">wu-etal-2024-pyvene</identifier>
<location>
<url>https://aclanthology.org/2024.naacl-demo.16</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>158</start>
<end>165</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T pyvene: A Library for Understanding and Improving PyTorch Models via Interventions
%A Wu, Zhengxuan
%A Geiger, Atticus
%A Arora, Aryaman
%A Huang, Jing
%A Wang, Zheng
%A Goodman, Noah
%A Manning, Christopher
%A Potts, Christopher
%Y Chang, Kai-Wei
%Y Lee, Annie
%Y Rajani, Nazneen
%S Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 3: System Demonstrations)
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F wu-etal-2024-pyvene
%X Interventions on model-internal states are fundamental operations in many areas of AI, including model editing, steering, robustness, and interpretability. To facilitate such research, we introduce pyvene, an open-source Python library that supports customizable interventions on a range of different PyTorch modules. pyvene supports complex intervention schemes with an intuitive configuration format, and its interventions can be static or include trainable parameters. We show how pyvene provides a unified and extensible framework for performing interventions on neural models and sharing the intervened upon models with others. We illustrate the power of the library via interpretability analyses using causal abstraction and knowledge localization. We publish our library through Python Package Index (PyPI) and provide code, documentation, and tutorials at ‘https://github.com/stanfordnlp/pyvene‘.
%U https://aclanthology.org/2024.naacl-demo.16
%P 158-165
Markdown (Informal)
[pyvene: A Library for Understanding and Improving PyTorch Models via Interventions](https://aclanthology.org/2024.naacl-demo.16) (Wu et al., NAACL 2024)
ACL
- Zhengxuan Wu, Atticus Geiger, Aryaman Arora, Jing Huang, Zheng Wang, Noah Goodman, Christopher Manning, and Christopher Potts. 2024. pyvene: A Library for Understanding and Improving PyTorch Models via Interventions. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 3: System Demonstrations), pages 158–165, Mexico City, Mexico. Association for Computational Linguistics.