@inproceedings{ibaraki-etal-2024-analyzing-occupational,
title = "Analyzing Occupational Distribution Representation in {J}apanese Language Models",
author = "Ibaraki, Katsumi and
Wu, Winston and
Wang, Lu and
Mihalcea, Rada",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.86",
pages = "959--973",
abstract = "Recent advances in large language models (LLMs) have enabled users to generate fluent and seemingly convincing text. However, these models have uneven performance in different languages, which is also associated with undesirable societal biases toward marginalized populations. Specifically, there is relatively little work on Japanese models, despite it being the thirteenth most widely spoken language. In this work, we first develop three Japanese language prompts to probe LLMs{'} understanding of Japanese names and their association between gender and occupations. We then evaluate a variety of English, multilingual, and Japanese models, correlating the models{'} outputs with occupation statistics from the Japanese Census Bureau from the last 100 years. Our findings indicate that models can associate Japanese names with the correct gendered occupations when using constrained decoding. However, with sampling or greedy decoding, Japanese language models have a preference for a small set of stereotypically gendered occupations, and multilingual models, though trained on Japanese, are not always able to understand Japanese prompts.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ibaraki-etal-2024-analyzing-occupational">
<titleInfo>
<title>Analyzing Occupational Distribution Representation in Japanese Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Katsumi</namePart>
<namePart type="family">Ibaraki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Winston</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rada</namePart>
<namePart type="family">Mihalcea</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</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">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</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>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recent advances in large language models (LLMs) have enabled users to generate fluent and seemingly convincing text. However, these models have uneven performance in different languages, which is also associated with undesirable societal biases toward marginalized populations. Specifically, there is relatively little work on Japanese models, despite it being the thirteenth most widely spoken language. In this work, we first develop three Japanese language prompts to probe LLMs’ understanding of Japanese names and their association between gender and occupations. We then evaluate a variety of English, multilingual, and Japanese models, correlating the models’ outputs with occupation statistics from the Japanese Census Bureau from the last 100 years. Our findings indicate that models can associate Japanese names with the correct gendered occupations when using constrained decoding. However, with sampling or greedy decoding, Japanese language models have a preference for a small set of stereotypically gendered occupations, and multilingual models, though trained on Japanese, are not always able to understand Japanese prompts.</abstract>
<identifier type="citekey">ibaraki-etal-2024-analyzing-occupational</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.86</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>959</start>
<end>973</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Analyzing Occupational Distribution Representation in Japanese Language Models
%A Ibaraki, Katsumi
%A Wu, Winston
%A Wang, Lu
%A Mihalcea, Rada
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F ibaraki-etal-2024-analyzing-occupational
%X Recent advances in large language models (LLMs) have enabled users to generate fluent and seemingly convincing text. However, these models have uneven performance in different languages, which is also associated with undesirable societal biases toward marginalized populations. Specifically, there is relatively little work on Japanese models, despite it being the thirteenth most widely spoken language. In this work, we first develop three Japanese language prompts to probe LLMs’ understanding of Japanese names and their association between gender and occupations. We then evaluate a variety of English, multilingual, and Japanese models, correlating the models’ outputs with occupation statistics from the Japanese Census Bureau from the last 100 years. Our findings indicate that models can associate Japanese names with the correct gendered occupations when using constrained decoding. However, with sampling or greedy decoding, Japanese language models have a preference for a small set of stereotypically gendered occupations, and multilingual models, though trained on Japanese, are not always able to understand Japanese prompts.
%U https://aclanthology.org/2024.lrec-main.86
%P 959-973
Markdown (Informal)
[Analyzing Occupational Distribution Representation in Japanese Language Models](https://aclanthology.org/2024.lrec-main.86) (Ibaraki et al., LREC-COLING 2024)
ACL