@inproceedings{jang-etal-2022-becel,
title = "{BECEL}: Benchmark for Consistency Evaluation of Language Models",
author = "Jang, Myeongjun and
Kwon, Deuk Sin and
Lukasiewicz, Thomas",
editor = "Calzolari, Nicoletta and
Huang, Chu-Ren and
Kim, Hansaem and
Pustejovsky, James and
Wanner, Leo and
Choi, Key-Sun and
Ryu, Pum-Mo and
Chen, Hsin-Hsi and
Donatelli, Lucia and
Ji, Heng and
Kurohashi, Sadao and
Paggio, Patrizia and
Xue, Nianwen and
Kim, Seokhwan and
Hahm, Younggyun and
He, Zhong and
Lee, Tony Kyungil and
Santus, Enrico and
Bond, Francis and
Na, Seung-Hoon",
booktitle = "Proceedings of the 29th International Conference on Computational Linguistics",
month = oct,
year = "2022",
address = "Gyeongju, Republic of Korea",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2022.coling-1.324/",
pages = "3680--3696",
abstract = "Behavioural consistency is a critical condition for a language model (LM) to become trustworthy like humans. Despite its importance, however, there is little consensus on the definition of LM consistency, resulting in different definitions across many studies. In this paper, we first propose the idea of LM consistency based on behavioural consistency and establish a taxonomy that classifies previously studied consistencies into several sub-categories. Next, we create a new benchmark that allows us to evaluate a model on 19 test cases, distinguished by multiple types of consistency and diverse downstream tasks. Through extensive experiments on the new benchmark, we ascertain that none of the modern pre-trained language models (PLMs) performs well in every test case, while exhibiting high inconsistency in many cases. Our experimental results suggest that a unified benchmark that covers broad aspects (i.e., multiple consistency types and tasks) is essential for a more precise evaluation."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jang-etal-2022-becel">
<titleInfo>
<title>BECEL: Benchmark for Consistency Evaluation of Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Myeongjun</namePart>
<namePart type="family">Jang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Deuk</namePart>
<namePart type="given">Sin</namePart>
<namePart type="family">Kwon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thomas</namePart>
<namePart type="family">Lukasiewicz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 29th International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chu-Ren</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hansaem</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">Pustejovsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Key-Sun</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pum-Mo</namePart>
<namePart type="family">Ryu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hsin-Hsi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Donatelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sadao</namePart>
<namePart type="family">Kurohashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrizia</namePart>
<namePart type="family">Paggio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seokhwan</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Younggyun</namePart>
<namePart type="family">Hahm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhong</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tony</namePart>
<namePart type="given">Kyungil</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enrico</namePart>
<namePart type="family">Santus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francis</namePart>
<namePart type="family">Bond</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seung-Hoon</namePart>
<namePart type="family">Na</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Gyeongju, Republic of Korea</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Behavioural consistency is a critical condition for a language model (LM) to become trustworthy like humans. Despite its importance, however, there is little consensus on the definition of LM consistency, resulting in different definitions across many studies. In this paper, we first propose the idea of LM consistency based on behavioural consistency and establish a taxonomy that classifies previously studied consistencies into several sub-categories. Next, we create a new benchmark that allows us to evaluate a model on 19 test cases, distinguished by multiple types of consistency and diverse downstream tasks. Through extensive experiments on the new benchmark, we ascertain that none of the modern pre-trained language models (PLMs) performs well in every test case, while exhibiting high inconsistency in many cases. Our experimental results suggest that a unified benchmark that covers broad aspects (i.e., multiple consistency types and tasks) is essential for a more precise evaluation.</abstract>
<identifier type="citekey">jang-etal-2022-becel</identifier>
<location>
<url>https://aclanthology.org/2022.coling-1.324/</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>3680</start>
<end>3696</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T BECEL: Benchmark for Consistency Evaluation of Language Models
%A Jang, Myeongjun
%A Kwon, Deuk Sin
%A Lukasiewicz, Thomas
%Y Calzolari, Nicoletta
%Y Huang, Chu-Ren
%Y Kim, Hansaem
%Y Pustejovsky, James
%Y Wanner, Leo
%Y Choi, Key-Sun
%Y Ryu, Pum-Mo
%Y Chen, Hsin-Hsi
%Y Donatelli, Lucia
%Y Ji, Heng
%Y Kurohashi, Sadao
%Y Paggio, Patrizia
%Y Xue, Nianwen
%Y Kim, Seokhwan
%Y Hahm, Younggyun
%Y He, Zhong
%Y Lee, Tony Kyungil
%Y Santus, Enrico
%Y Bond, Francis
%Y Na, Seung-Hoon
%S Proceedings of the 29th International Conference on Computational Linguistics
%D 2022
%8 October
%I International Committee on Computational Linguistics
%C Gyeongju, Republic of Korea
%F jang-etal-2022-becel
%X Behavioural consistency is a critical condition for a language model (LM) to become trustworthy like humans. Despite its importance, however, there is little consensus on the definition of LM consistency, resulting in different definitions across many studies. In this paper, we first propose the idea of LM consistency based on behavioural consistency and establish a taxonomy that classifies previously studied consistencies into several sub-categories. Next, we create a new benchmark that allows us to evaluate a model on 19 test cases, distinguished by multiple types of consistency and diverse downstream tasks. Through extensive experiments on the new benchmark, we ascertain that none of the modern pre-trained language models (PLMs) performs well in every test case, while exhibiting high inconsistency in many cases. Our experimental results suggest that a unified benchmark that covers broad aspects (i.e., multiple consistency types and tasks) is essential for a more precise evaluation.
%U https://aclanthology.org/2022.coling-1.324/
%P 3680-3696
Markdown (Informal)
[BECEL: Benchmark for Consistency Evaluation of Language Models](https://aclanthology.org/2022.coling-1.324/) (Jang et al., COLING 2022)
ACL