@inproceedings{idahl-etal-2021-towards,
title = "Towards Benchmarking the Utility of Explanations for Model Debugging",
author = "Idahl, Maximilian and
Lyu, Lijun and
Gadiraju, Ujwal and
Anand, Avishek",
editor = "Pruksachatkun, Yada and
Ramakrishna, Anil and
Chang, Kai-Wei and
Krishna, Satyapriya and
Dhamala, Jwala and
Guha, Tanaya and
Ren, Xiang",
booktitle = "Proceedings of the First Workshop on Trustworthy Natural Language Processing",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.trustnlp-1.8",
doi = "10.18653/v1/2021.trustnlp-1.8",
pages = "68--73",
abstract = "Post-hoc explanation methods are an important class of approaches that help understand the rationale underlying a trained model{'}s decision. But how useful are they for an end-user towards accomplishing a given task? In this vision paper, we argue the need for a benchmark to facilitate evaluations of the utility of post-hoc explanation methods. As a first step to this end, we enumerate desirable properties that such a benchmark should possess for the task of debugging text classifiers. Additionally, we highlight that such a benchmark facilitates not only assessing the effectiveness of explanations but also their efficiency.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="idahl-etal-2021-towards">
<titleInfo>
<title>Towards Benchmarking the Utility of Explanations for Model Debugging</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maximilian</namePart>
<namePart type="family">Idahl</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lijun</namePart>
<namePart type="family">Lyu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ujwal</namePart>
<namePart type="family">Gadiraju</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Avishek</namePart>
<namePart type="family">Anand</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the First Workshop on Trustworthy Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yada</namePart>
<namePart type="family">Pruksachatkun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anil</namePart>
<namePart type="family">Ramakrishna</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<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">Satyapriya</namePart>
<namePart type="family">Krishna</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jwala</namePart>
<namePart type="family">Dhamala</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanaya</namePart>
<namePart type="family">Guha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiang</namePart>
<namePart type="family">Ren</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Post-hoc explanation methods are an important class of approaches that help understand the rationale underlying a trained model’s decision. But how useful are they for an end-user towards accomplishing a given task? In this vision paper, we argue the need for a benchmark to facilitate evaluations of the utility of post-hoc explanation methods. As a first step to this end, we enumerate desirable properties that such a benchmark should possess for the task of debugging text classifiers. Additionally, we highlight that such a benchmark facilitates not only assessing the effectiveness of explanations but also their efficiency.</abstract>
<identifier type="citekey">idahl-etal-2021-towards</identifier>
<identifier type="doi">10.18653/v1/2021.trustnlp-1.8</identifier>
<location>
<url>https://aclanthology.org/2021.trustnlp-1.8</url>
</location>
<part>
<date>2021-06</date>
<extent unit="page">
<start>68</start>
<end>73</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Towards Benchmarking the Utility of Explanations for Model Debugging
%A Idahl, Maximilian
%A Lyu, Lijun
%A Gadiraju, Ujwal
%A Anand, Avishek
%Y Pruksachatkun, Yada
%Y Ramakrishna, Anil
%Y Chang, Kai-Wei
%Y Krishna, Satyapriya
%Y Dhamala, Jwala
%Y Guha, Tanaya
%Y Ren, Xiang
%S Proceedings of the First Workshop on Trustworthy Natural Language Processing
%D 2021
%8 June
%I Association for Computational Linguistics
%C Online
%F idahl-etal-2021-towards
%X Post-hoc explanation methods are an important class of approaches that help understand the rationale underlying a trained model’s decision. But how useful are they for an end-user towards accomplishing a given task? In this vision paper, we argue the need for a benchmark to facilitate evaluations of the utility of post-hoc explanation methods. As a first step to this end, we enumerate desirable properties that such a benchmark should possess for the task of debugging text classifiers. Additionally, we highlight that such a benchmark facilitates not only assessing the effectiveness of explanations but also their efficiency.
%R 10.18653/v1/2021.trustnlp-1.8
%U https://aclanthology.org/2021.trustnlp-1.8
%U https://doi.org/10.18653/v1/2021.trustnlp-1.8
%P 68-73
Markdown (Informal)
[Towards Benchmarking the Utility of Explanations for Model Debugging](https://aclanthology.org/2021.trustnlp-1.8) (Idahl et al., TrustNLP 2021)
ACL