@inproceedings{hossain-etal-2023-misgendered,
title = "{MISGENDERED}: Limits of Large Language Models in Understanding Pronouns",
author = "Hossain, Tamanna and
Dev, Sunipa and
Singh, Sameer",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.acl-long.293",
doi = "10.18653/v1/2023.acl-long.293",
pages = "5352--5367",
abstract = "Content Warning: This paper contains examples of misgendering and erasure that could be offensive and potentially triggering. Gender bias in language technologies has been widely studied, but research has mostly been restricted to a binary paradigm of gender. It is essential also to consider non-binary gender identities, as excluding them can cause further harm to an already marginalized group. In this paper, we comprehensively evaluate popular language models for their ability to correctly use English gender-neutral pronouns (e.g., singular they, them) and neo-pronouns (e.g., ze, xe, thon) that are used by individuals whose gender identity is not represented by binary pronouns. We introduce Misgendered, a framework for evaluating large language models{'} ability to correctly use preferred pronouns, consisting of (i) instances declaring an individual{'}s pronoun, followed by a sentence with a missing pronoun, and (ii) an experimental setup for evaluating masked and auto-regressive language models using a unified method. When prompted out-of-the-box, language models perform poorly at correctly predicting neo-pronouns (averaging 7.6{\%} accuracy) and gender-neutral pronouns (averaging 31.0{\%} accuracy). This inability to generalize results from a lack of representation of non-binary pronouns in training data and memorized associations. Few-shot adaptation with explicit examples in the prompt improves the performance but plateaus at only 45.4{\%} for neo-pronouns. We release the full dataset, code, and demo at \url{https://tamannahossainkay.github.io/misgendered/}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hossain-etal-2023-misgendered">
<titleInfo>
<title>MISGENDERED: Limits of Large Language Models in Understanding Pronouns</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tamanna</namePart>
<namePart type="family">Hossain</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sameer</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Content Warning: This paper contains examples of misgendering and erasure that could be offensive and potentially triggering. Gender bias in language technologies has been widely studied, but research has mostly been restricted to a binary paradigm of gender. It is essential also to consider non-binary gender identities, as excluding them can cause further harm to an already marginalized group. In this paper, we comprehensively evaluate popular language models for their ability to correctly use English gender-neutral pronouns (e.g., singular they, them) and neo-pronouns (e.g., ze, xe, thon) that are used by individuals whose gender identity is not represented by binary pronouns. We introduce Misgendered, a framework for evaluating large language models’ ability to correctly use preferred pronouns, consisting of (i) instances declaring an individual’s pronoun, followed by a sentence with a missing pronoun, and (ii) an experimental setup for evaluating masked and auto-regressive language models using a unified method. When prompted out-of-the-box, language models perform poorly at correctly predicting neo-pronouns (averaging 7.6% accuracy) and gender-neutral pronouns (averaging 31.0% accuracy). This inability to generalize results from a lack of representation of non-binary pronouns in training data and memorized associations. Few-shot adaptation with explicit examples in the prompt improves the performance but plateaus at only 45.4% for neo-pronouns. We release the full dataset, code, and demo at https://tamannahossainkay.github.io/misgendered/.</abstract>
<identifier type="citekey">hossain-etal-2023-misgendered</identifier>
<identifier type="doi">10.18653/v1/2023.acl-long.293</identifier>
<location>
<url>https://aclanthology.org/2023.acl-long.293</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>5352</start>
<end>5367</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MISGENDERED: Limits of Large Language Models in Understanding Pronouns
%A Hossain, Tamanna
%A Dev, Sunipa
%A Singh, Sameer
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F hossain-etal-2023-misgendered
%X Content Warning: This paper contains examples of misgendering and erasure that could be offensive and potentially triggering. Gender bias in language technologies has been widely studied, but research has mostly been restricted to a binary paradigm of gender. It is essential also to consider non-binary gender identities, as excluding them can cause further harm to an already marginalized group. In this paper, we comprehensively evaluate popular language models for their ability to correctly use English gender-neutral pronouns (e.g., singular they, them) and neo-pronouns (e.g., ze, xe, thon) that are used by individuals whose gender identity is not represented by binary pronouns. We introduce Misgendered, a framework for evaluating large language models’ ability to correctly use preferred pronouns, consisting of (i) instances declaring an individual’s pronoun, followed by a sentence with a missing pronoun, and (ii) an experimental setup for evaluating masked and auto-regressive language models using a unified method. When prompted out-of-the-box, language models perform poorly at correctly predicting neo-pronouns (averaging 7.6% accuracy) and gender-neutral pronouns (averaging 31.0% accuracy). This inability to generalize results from a lack of representation of non-binary pronouns in training data and memorized associations. Few-shot adaptation with explicit examples in the prompt improves the performance but plateaus at only 45.4% for neo-pronouns. We release the full dataset, code, and demo at https://tamannahossainkay.github.io/misgendered/.
%R 10.18653/v1/2023.acl-long.293
%U https://aclanthology.org/2023.acl-long.293
%U https://doi.org/10.18653/v1/2023.acl-long.293
%P 5352-5367
Markdown (Informal)
[MISGENDERED: Limits of Large Language Models in Understanding Pronouns](https://aclanthology.org/2023.acl-long.293) (Hossain et al., ACL 2023)
ACL