@inproceedings{belosevic-2026-invisible-speakers,
title = "Invisible Speakers? Gender Disparity in {G}erman {AI} Discourse and Its Reflection in Language Models",
author = "Belosevic, Milena",
editor = "Alves, Diego and
Bizzoni, Yuri and
Degaetano-Ortlieb, Stefania and
Kazantseva, Anna and
Pagel, Janis and
Szpakowicz, Stan",
booktitle = "Proceedings of the 10th Joint {SIGHUM} Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature 2026",
month = mar,
year = "2026",
address = "Rabat, Morocco",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.latechclfl-1.7/",
pages = "66--79",
ISBN = "979-8-89176-373-9",
abstract = {This paper investigates how language models (LMs) reproduce the existing gender disparity found in German media discourse about artificial intelligence (AI). Building on a human-annotated corpus of quotations from German media discourse on AI, we first quantify the frequency with which male and female speakers are directly cited across domains and speaker roles. We then train LL{\"a}Mmlein (Pfister et al., 2025), a state-of-the-art German-only language model, GBERT, and a logistic regression model using only the quoted text as input and without providing any gender cues to classify the quotation as originating from a male or female speaker. By comparing model predictions with corpus-based gold labels, we find that male voices dominate both the corpus and the model predictions. Balancing the data mitigates but does not fully eliminate this disparity, indicating that the strong male-default tendency of transformer models cannot be explained by corpus skew alone, but also by their priors from pretraining. The study contributes to the interpretability of language models' output for DH-related tasks, adaptation of NLP tools to domain-specific humanities corpora, and knowledge modelling in the humanities.}
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="belosevic-2026-invisible-speakers">
<titleInfo>
<title>Invisible Speakers? Gender Disparity in German AI Discourse and Its Reflection in Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Milena</namePart>
<namePart type="family">Belosevic</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 10th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Diego</namePart>
<namePart type="family">Alves</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuri</namePart>
<namePart type="family">Bizzoni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stefania</namePart>
<namePart type="family">Degaetano-Ortlieb</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Kazantseva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Janis</namePart>
<namePart type="family">Pagel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stan</namePart>
<namePart type="family">Szpakowicz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Rabat, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-373-9</identifier>
</relatedItem>
<abstract>This paper investigates how language models (LMs) reproduce the existing gender disparity found in German media discourse about artificial intelligence (AI). Building on a human-annotated corpus of quotations from German media discourse on AI, we first quantify the frequency with which male and female speakers are directly cited across domains and speaker roles. We then train LLäMmlein (Pfister et al., 2025), a state-of-the-art German-only language model, GBERT, and a logistic regression model using only the quoted text as input and without providing any gender cues to classify the quotation as originating from a male or female speaker. By comparing model predictions with corpus-based gold labels, we find that male voices dominate both the corpus and the model predictions. Balancing the data mitigates but does not fully eliminate this disparity, indicating that the strong male-default tendency of transformer models cannot be explained by corpus skew alone, but also by their priors from pretraining. The study contributes to the interpretability of language models’ output for DH-related tasks, adaptation of NLP tools to domain-specific humanities corpora, and knowledge modelling in the humanities.</abstract>
<identifier type="citekey">belosevic-2026-invisible-speakers</identifier>
<location>
<url>https://aclanthology.org/2026.latechclfl-1.7/</url>
</location>
<part>
<date>2026-03</date>
<extent unit="page">
<start>66</start>
<end>79</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Invisible Speakers? Gender Disparity in German AI Discourse and Its Reflection in Language Models
%A Belosevic, Milena
%Y Alves, Diego
%Y Bizzoni, Yuri
%Y Degaetano-Ortlieb, Stefania
%Y Kazantseva, Anna
%Y Pagel, Janis
%Y Szpakowicz, Stan
%S Proceedings of the 10th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature 2026
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%@ 979-8-89176-373-9
%F belosevic-2026-invisible-speakers
%X This paper investigates how language models (LMs) reproduce the existing gender disparity found in German media discourse about artificial intelligence (AI). Building on a human-annotated corpus of quotations from German media discourse on AI, we first quantify the frequency with which male and female speakers are directly cited across domains and speaker roles. We then train LLäMmlein (Pfister et al., 2025), a state-of-the-art German-only language model, GBERT, and a logistic regression model using only the quoted text as input and without providing any gender cues to classify the quotation as originating from a male or female speaker. By comparing model predictions with corpus-based gold labels, we find that male voices dominate both the corpus and the model predictions. Balancing the data mitigates but does not fully eliminate this disparity, indicating that the strong male-default tendency of transformer models cannot be explained by corpus skew alone, but also by their priors from pretraining. The study contributes to the interpretability of language models’ output for DH-related tasks, adaptation of NLP tools to domain-specific humanities corpora, and knowledge modelling in the humanities.
%U https://aclanthology.org/2026.latechclfl-1.7/
%P 66-79
Markdown (Informal)
[Invisible Speakers? Gender Disparity in German AI Discourse and Its Reflection in Language Models](https://aclanthology.org/2026.latechclfl-1.7/) (Belosevic, LaTeCH-CLfL 2026)
ACL