@inproceedings{esfahani-etal-2026-working,
title = "{I} Am Working So Hard, Can{'}t You See?: Physical vs. Cognitive Labor Gender Bias in {LLM}s in {P}ersian and {E}nglish",
author = "Esfahani, Elham Vatankhahan and
Khorshid, Sahar Bahrami and
Golshaie, Ramin",
editor = "Fale{\'n}ska, Agnieszka and
Basta, Christine and
Costa-juss{\`a}, Marta and
Sta{\'n}czak, Karolina and
Nozza, Debora and
Attanasio, Giuseppe and
Neplenbroek, Vera and
Hardmeier, Christian",
booktitle = "Proceedings of the 7th Workshop on Gender Bias in Natural Language Processing ({G}e{BNLP})",
month = nov,
year = "2026",
address = "Hengqin, China (remote)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.gebnlp-1.14/",
pages = "193--206",
ISBN = "979-8-89176-447-7",
abstract = "Gender bias in LLMs has been documented across many overt domains, such as colors, emotions, and occupations, while subtler forms rooted in household labor remain understudied. Following Daminger (2019), we distinguish physical household tasks from their cognitive counterparts, which are rarely recognized as labor despite being time-consuming. We adapt the name-generation probing method of Kalhor and Bahrak (2025) to ten household domains, each phrased as both a physical task and its cognitive counterpart, and evaluate six open-source models from three model families in Persian and English. On average, cognitive tasks receive a higher share of feminine names than their physical counterparts in both languages (Wilcoxon signed-rank test); the direction holds in 8 of 10 domains in Persian and 6 of 10 in English. Averaged over models and tasks, skew toward one gender is larger in English than in Persian, in contrast to the overall pattern reported for other domains, but prompts and labeling procedures differ across languages, so we treat this comparison as suggestive. Our results indicate that the cross-linguistic strength of gender bias depends on the domain and model rather than being a fixed property of a language pair."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="esfahani-etal-2026-working">
<titleInfo>
<title>I Am Working So Hard, Can’t You See?: Physical vs. Cognitive Labor Gender Bias in LLMs in Persian and English</title>
</titleInfo>
<name type="personal">
<namePart type="given">Elham</namePart>
<namePart type="given">Vatankhahan</namePart>
<namePart type="family">Esfahani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sahar</namePart>
<namePart type="given">Bahrami</namePart>
<namePart type="family">Khorshid</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ramin</namePart>
<namePart type="family">Golshaie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 7th Workshop on Gender Bias in Natural Language Processing (GeBNLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Agnieszka</namePart>
<namePart type="family">Faleńska</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christine</namePart>
<namePart type="family">Basta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marta</namePart>
<namePart type="family">Costa-jussà</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Karolina</namePart>
<namePart type="family">Stańczak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Debora</namePart>
<namePart type="family">Nozza</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Giuseppe</namePart>
<namePart type="family">Attanasio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vera</namePart>
<namePart type="family">Neplenbroek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christian</namePart>
<namePart type="family">Hardmeier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hengqin, China (remote)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-447-7</identifier>
</relatedItem>
<abstract>Gender bias in LLMs has been documented across many overt domains, such as colors, emotions, and occupations, while subtler forms rooted in household labor remain understudied. Following Daminger (2019), we distinguish physical household tasks from their cognitive counterparts, which are rarely recognized as labor despite being time-consuming. We adapt the name-generation probing method of Kalhor and Bahrak (2025) to ten household domains, each phrased as both a physical task and its cognitive counterpart, and evaluate six open-source models from three model families in Persian and English. On average, cognitive tasks receive a higher share of feminine names than their physical counterparts in both languages (Wilcoxon signed-rank test); the direction holds in 8 of 10 domains in Persian and 6 of 10 in English. Averaged over models and tasks, skew toward one gender is larger in English than in Persian, in contrast to the overall pattern reported for other domains, but prompts and labeling procedures differ across languages, so we treat this comparison as suggestive. Our results indicate that the cross-linguistic strength of gender bias depends on the domain and model rather than being a fixed property of a language pair.</abstract>
<identifier type="citekey">esfahani-etal-2026-working</identifier>
<location>
<url>https://aclanthology.org/2026.gebnlp-1.14/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>193</start>
<end>206</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T I Am Working So Hard, Can’t You See?: Physical vs. Cognitive Labor Gender Bias in LLMs in Persian and English
%A Esfahani, Elham Vatankhahan
%A Khorshid, Sahar Bahrami
%A Golshaie, Ramin
%Y Faleńska, Agnieszka
%Y Basta, Christine
%Y Costa-jussà, Marta
%Y Stańczak, Karolina
%Y Nozza, Debora
%Y Attanasio, Giuseppe
%Y Neplenbroek, Vera
%Y Hardmeier, Christian
%S Proceedings of the 7th Workshop on Gender Bias in Natural Language Processing (GeBNLP)
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, China (remote)
%@ 979-8-89176-447-7
%F esfahani-etal-2026-working
%X Gender bias in LLMs has been documented across many overt domains, such as colors, emotions, and occupations, while subtler forms rooted in household labor remain understudied. Following Daminger (2019), we distinguish physical household tasks from their cognitive counterparts, which are rarely recognized as labor despite being time-consuming. We adapt the name-generation probing method of Kalhor and Bahrak (2025) to ten household domains, each phrased as both a physical task and its cognitive counterpart, and evaluate six open-source models from three model families in Persian and English. On average, cognitive tasks receive a higher share of feminine names than their physical counterparts in both languages (Wilcoxon signed-rank test); the direction holds in 8 of 10 domains in Persian and 6 of 10 in English. Averaged over models and tasks, skew toward one gender is larger in English than in Persian, in contrast to the overall pattern reported for other domains, but prompts and labeling procedures differ across languages, so we treat this comparison as suggestive. Our results indicate that the cross-linguistic strength of gender bias depends on the domain and model rather than being a fixed property of a language pair.
%U https://aclanthology.org/2026.gebnlp-1.14/
%P 193-206
Markdown (Informal)
[I Am Working So Hard, Can’t You See?: Physical vs. Cognitive Labor Gender Bias in LLMs in Persian and English](https://aclanthology.org/2026.gebnlp-1.14/) (Esfahani et al., GeBNLP 2026)
ACL