@inproceedings{janzen-etal-2026-gendered,
title = "Gendered Prompting and {LLM} Code Review: How Gender Cues in the Prompt Shape Code Quality and Evaluation",
author = {Janzen, Lynn and
Eroglu, {\"U}veys and
Kolossa, Dorothea and
Knoeferle, Pia and
M{\"o}ller, Sebastian and
Schmitt, Vera and
Solopova, Veronika},
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-main.1081/",
pages = "24834--24852",
ISBN = "979-8-89176-459-0",
abstract = "LLMs are increasingly embedded in programming workflows, from code generation to automated code review. Yet, how gendered communication styles interact with LLM-assisted programming and code review remains underexplored. We present a mixed-methods pilot study examining whether gender-related linguistic differences in prompts influence code generation outcomes and code review decisions. Across three complementary studies, we analyze (i) collected real-world coding prompts, (ii) a user study, in which developers solve identical programming tasks with LLM assistance, and (iii) an LLM-based simulated evaluation framework that systematically varies gender-coded prompt styles and reviewer personas. We find that gender-related differences in prompting style are subtle but measurable, with female-authored prompts exhibiting more indirect and involved language, which does not translate into consistent gaps in functional correctness or static code quality. For LLM code review, in contrast, we observe systematic biases: on average, models approve female-authored code more, despite comparable quality. Our experiments show that gender-coded prompt styles influence code length and maintainability. We also observe substantial variation in reviewer behavior across models. Together, these findings suggest that fairness risks in LLM-assisted programming arise less from code generation accuracy than from LLM-based evaluation, particularly as LLMs are increasingly used as automated code reviewers."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="janzen-etal-2026-gendered">
<titleInfo>
<title>Gendered Prompting and LLM Code Review: How Gender Cues in the Prompt Shape Code Quality and Evaluation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lynn</namePart>
<namePart type="family">Janzen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Üveys</namePart>
<namePart type="family">Eroglu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dorothea</namePart>
<namePart type="family">Kolossa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pia</namePart>
<namePart type="family">Knoeferle</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Möller</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vera</namePart>
<namePart type="family">Schmitt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronika</namePart>
<namePart type="family">Solopova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-459-0</identifier>
</relatedItem>
<abstract>LLMs are increasingly embedded in programming workflows, from code generation to automated code review. Yet, how gendered communication styles interact with LLM-assisted programming and code review remains underexplored. We present a mixed-methods pilot study examining whether gender-related linguistic differences in prompts influence code generation outcomes and code review decisions. Across three complementary studies, we analyze (i) collected real-world coding prompts, (ii) a user study, in which developers solve identical programming tasks with LLM assistance, and (iii) an LLM-based simulated evaluation framework that systematically varies gender-coded prompt styles and reviewer personas. We find that gender-related differences in prompting style are subtle but measurable, with female-authored prompts exhibiting more indirect and involved language, which does not translate into consistent gaps in functional correctness or static code quality. For LLM code review, in contrast, we observe systematic biases: on average, models approve female-authored code more, despite comparable quality. Our experiments show that gender-coded prompt styles influence code length and maintainability. We also observe substantial variation in reviewer behavior across models. Together, these findings suggest that fairness risks in LLM-assisted programming arise less from code generation accuracy than from LLM-based evaluation, particularly as LLMs are increasingly used as automated code reviewers.</abstract>
<identifier type="citekey">janzen-etal-2026-gendered</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.1081/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>24834</start>
<end>24852</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Gendered Prompting and LLM Code Review: How Gender Cues in the Prompt Shape Code Quality and Evaluation
%A Janzen, Lynn
%A Eroglu, Üveys
%A Kolossa, Dorothea
%A Knoeferle, Pia
%A Möller, Sebastian
%A Schmitt, Vera
%A Solopova, Veronika
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F janzen-etal-2026-gendered
%X LLMs are increasingly embedded in programming workflows, from code generation to automated code review. Yet, how gendered communication styles interact with LLM-assisted programming and code review remains underexplored. We present a mixed-methods pilot study examining whether gender-related linguistic differences in prompts influence code generation outcomes and code review decisions. Across three complementary studies, we analyze (i) collected real-world coding prompts, (ii) a user study, in which developers solve identical programming tasks with LLM assistance, and (iii) an LLM-based simulated evaluation framework that systematically varies gender-coded prompt styles and reviewer personas. We find that gender-related differences in prompting style are subtle but measurable, with female-authored prompts exhibiting more indirect and involved language, which does not translate into consistent gaps in functional correctness or static code quality. For LLM code review, in contrast, we observe systematic biases: on average, models approve female-authored code more, despite comparable quality. Our experiments show that gender-coded prompt styles influence code length and maintainability. We also observe substantial variation in reviewer behavior across models. Together, these findings suggest that fairness risks in LLM-assisted programming arise less from code generation accuracy than from LLM-based evaluation, particularly as LLMs are increasingly used as automated code reviewers.
%U https://aclanthology.org/2026.emnlp-main.1081/
%P 24834-24852
Markdown (Informal)
[Gendered Prompting and LLM Code Review: How Gender Cues in the Prompt Shape Code Quality and Evaluation](https://aclanthology.org/2026.emnlp-main.1081/) (Janzen et al., EMNLP 2026)
ACL