@inproceedings{leonardelli-etal-2026-real,
title = "Real Men are Tough: Evaluating Gender Bias and Sensitivity to Masculinity Norms in {LLM}s",
author = "Leonardelli, Elisa and
Casula, Camilla and
Nyul, Boglarka and
Tonelli, Sara",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-acl.225/",
pages = "4609--4626",
ISBN = "979-8-89176-395-1",
abstract = "Large language models (LLMs) are known to exhibit gender bias, yet most evaluations focus on downstream stereotypes rather than the normative frameworks that shape model inference. We investigate whether LLMs rely on traditional masculinity norms (e.g. ``real men are tough'') as latent priors in gender-biased inference. We ground our evaluation in the Male Role Norms Inventory (MRNI), a validated psychological framework of prescriptive male role norms.Anchored in MRNI items, we probe models using two complementary approaches: (i) explicit Likert-style agreement with masculinity norms, and (ii) a newly crafted English-Italian scenario-based inference dataset (MRNI-BB), in which gender information and evidential support are systematically varied. Across models, explicit endorsement of masculinity norms is generally low. In contrast, in scenario-based inference tasks, models systematically attribute MRNI-aligned behaviors to male agents, even when evidence is ambiguous or absent. This effect disappears when gender markers are removed, suggesting that masculinity norms are treated as gender-specific expectations about male agents. Increasing model scale reduces explicit norm endorsement but is associated with stronger male-directed bias under uncertainty."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="leonardelli-etal-2026-real">
<titleInfo>
<title>Real Men are Tough: Evaluating Gender Bias and Sensitivity to Masculinity Norms in LLMs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Elisa</namePart>
<namePart type="family">Leonardelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Camilla</namePart>
<namePart type="family">Casula</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Boglarka</namePart>
<namePart type="family">Nyul</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Tonelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-395-1</identifier>
</relatedItem>
<abstract>Large language models (LLMs) are known to exhibit gender bias, yet most evaluations focus on downstream stereotypes rather than the normative frameworks that shape model inference. We investigate whether LLMs rely on traditional masculinity norms (e.g. “real men are tough”) as latent priors in gender-biased inference. We ground our evaluation in the Male Role Norms Inventory (MRNI), a validated psychological framework of prescriptive male role norms.Anchored in MRNI items, we probe models using two complementary approaches: (i) explicit Likert-style agreement with masculinity norms, and (ii) a newly crafted English-Italian scenario-based inference dataset (MRNI-BB), in which gender information and evidential support are systematically varied. Across models, explicit endorsement of masculinity norms is generally low. In contrast, in scenario-based inference tasks, models systematically attribute MRNI-aligned behaviors to male agents, even when evidence is ambiguous or absent. This effect disappears when gender markers are removed, suggesting that masculinity norms are treated as gender-specific expectations about male agents. Increasing model scale reduces explicit norm endorsement but is associated with stronger male-directed bias under uncertainty.</abstract>
<identifier type="citekey">leonardelli-etal-2026-real</identifier>
<location>
<url>https://aclanthology.org/2026.findings-acl.225/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>4609</start>
<end>4626</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Real Men are Tough: Evaluating Gender Bias and Sensitivity to Masculinity Norms in LLMs
%A Leonardelli, Elisa
%A Casula, Camilla
%A Nyul, Boglarka
%A Tonelli, Sara
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Findings of the Association for Computational Linguistics: ACL 2026
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-395-1
%F leonardelli-etal-2026-real
%X Large language models (LLMs) are known to exhibit gender bias, yet most evaluations focus on downstream stereotypes rather than the normative frameworks that shape model inference. We investigate whether LLMs rely on traditional masculinity norms (e.g. “real men are tough”) as latent priors in gender-biased inference. We ground our evaluation in the Male Role Norms Inventory (MRNI), a validated psychological framework of prescriptive male role norms.Anchored in MRNI items, we probe models using two complementary approaches: (i) explicit Likert-style agreement with masculinity norms, and (ii) a newly crafted English-Italian scenario-based inference dataset (MRNI-BB), in which gender information and evidential support are systematically varied. Across models, explicit endorsement of masculinity norms is generally low. In contrast, in scenario-based inference tasks, models systematically attribute MRNI-aligned behaviors to male agents, even when evidence is ambiguous or absent. This effect disappears when gender markers are removed, suggesting that masculinity norms are treated as gender-specific expectations about male agents. Increasing model scale reduces explicit norm endorsement but is associated with stronger male-directed bias under uncertainty.
%U https://aclanthology.org/2026.findings-acl.225/
%P 4609-4626
Markdown (Informal)
[Real Men are Tough: Evaluating Gender Bias and Sensitivity to Masculinity Norms in LLMs](https://aclanthology.org/2026.findings-acl.225/) (Leonardelli et al., Findings 2026)
ACL