@inproceedings{xie-etal-2024-ivra,
title = "{I}v{RA}: A Framework to Enhance Attention-Based Explanations for Language Models with Interpretability-Driven Training",
author = "Xie, Sean and
Vosoughi, Soroush and
Hassanpour, Saeed",
editor = "Belinkov, Yonatan and
Kim, Najoung and
Jumelet, Jaap and
Mohebbi, Hosein and
Mueller, Aaron and
Chen, Hanjie",
booktitle = "Proceedings of the 7th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP",
month = nov,
year = "2024",
address = "Miami, Florida, US",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.blackboxnlp-1.27",
pages = "431--451",
abstract = "Attention has long served as a foundational technique for generating explanations. With the recent developments made in Explainable AI (XAI), the multi-faceted nature of interpretability has become more apparent. Can attention, as an explanation method, be adapted to meet the diverse needs that our expanded understanding of interpretability demands? In this work, we aim to address this question by introducing IvRA, a framework designed to directly train a language model{'}s attention distribution through regularization to produce attribution explanations that align with interpretability criteria such as simulatability, faithfulness, and consistency. Our extensive experimental analysis demonstrates that IvRA outperforms existing methods in guiding language models to generate explanations that are simulatable, faithful, and consistent, in tandem with their predictions. Furthermore, we perform ablation studies to verify the robustness of IvRA across various experimental settings and to shed light on the interactions among different interpretability criteria.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xie-etal-2024-ivra">
<titleInfo>
<title>IvRA: A Framework to Enhance Attention-Based Explanations for Language Models with Interpretability-Driven Training</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sean</namePart>
<namePart type="family">Xie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Soroush</namePart>
<namePart type="family">Vosoughi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Saeed</namePart>
<namePart type="family">Hassanpour</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 7th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yonatan</namePart>
<namePart type="family">Belinkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Najoung</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jaap</namePart>
<namePart type="family">Jumelet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hosein</namePart>
<namePart type="family">Mohebbi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aaron</namePart>
<namePart type="family">Mueller</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hanjie</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, US</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Attention has long served as a foundational technique for generating explanations. With the recent developments made in Explainable AI (XAI), the multi-faceted nature of interpretability has become more apparent. Can attention, as an explanation method, be adapted to meet the diverse needs that our expanded understanding of interpretability demands? In this work, we aim to address this question by introducing IvRA, a framework designed to directly train a language model’s attention distribution through regularization to produce attribution explanations that align with interpretability criteria such as simulatability, faithfulness, and consistency. Our extensive experimental analysis demonstrates that IvRA outperforms existing methods in guiding language models to generate explanations that are simulatable, faithful, and consistent, in tandem with their predictions. Furthermore, we perform ablation studies to verify the robustness of IvRA across various experimental settings and to shed light on the interactions among different interpretability criteria.</abstract>
<identifier type="citekey">xie-etal-2024-ivra</identifier>
<location>
<url>https://aclanthology.org/2024.blackboxnlp-1.27</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>431</start>
<end>451</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T IvRA: A Framework to Enhance Attention-Based Explanations for Language Models with Interpretability-Driven Training
%A Xie, Sean
%A Vosoughi, Soroush
%A Hassanpour, Saeed
%Y Belinkov, Yonatan
%Y Kim, Najoung
%Y Jumelet, Jaap
%Y Mohebbi, Hosein
%Y Mueller, Aaron
%Y Chen, Hanjie
%S Proceedings of the 7th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, US
%F xie-etal-2024-ivra
%X Attention has long served as a foundational technique for generating explanations. With the recent developments made in Explainable AI (XAI), the multi-faceted nature of interpretability has become more apparent. Can attention, as an explanation method, be adapted to meet the diverse needs that our expanded understanding of interpretability demands? In this work, we aim to address this question by introducing IvRA, a framework designed to directly train a language model’s attention distribution through regularization to produce attribution explanations that align with interpretability criteria such as simulatability, faithfulness, and consistency. Our extensive experimental analysis demonstrates that IvRA outperforms existing methods in guiding language models to generate explanations that are simulatable, faithful, and consistent, in tandem with their predictions. Furthermore, we perform ablation studies to verify the robustness of IvRA across various experimental settings and to shed light on the interactions among different interpretability criteria.
%U https://aclanthology.org/2024.blackboxnlp-1.27
%P 431-451
Markdown (Informal)
[IvRA: A Framework to Enhance Attention-Based Explanations for Language Models with Interpretability-Driven Training](https://aclanthology.org/2024.blackboxnlp-1.27) (Xie et al., BlackboxNLP 2024)
ACL