@inproceedings{nguyen-etal-2025-leveraging,
title = "Leveraging Large Language Models in Detecting Anti-{LGBTQIA}+ User-generated Texts",
author = "Nguyen, Quoc-Toan and
Nguyen, Josh and
Pham, Tuan and
Teahan, William John",
editor = "Pranav, A and
Valentine, Alissa and
Bhatt, Shaily and
Long, Yanan and
Subramonian, Arjun and
Bertsch, Amanda and
Lauscher, Anne and
Gupta, Ankush",
booktitle = "Proceedings of the Queer in AI Workshop",
month = may,
year = "2025",
address = "Hybrid format (in-person and virtual)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.queerinai-main.4/",
doi = "10.18653/v1/2025.queerinai-main.4",
pages = "26--34",
ISBN = "979-8-89176-244-2",
abstract = "Anti-LGBTQIA+ texts in user-generated content pose significant risks to online safety and inclusivity. This study investigates the capabilities and limitations of five widely adopted Large Language Models (LLMs){---}DeepSeek-V3, GPT-4o, GPT-4o-mini, GPT-o1-mini, and Llama3.3-70B{---}in detecting such harmful content. Our findings reveal that while LLMs demonstrate potential in identifying offensive language, their effectiveness varies across models and metrics, with notable shortcomings in calibration. Furthermore, linguistic analysis exposes deeply embedded patterns of discrimination, reinforcing the urgency for improved detection mechanisms for this marginalised population. In summary, this study demonstrates the significant potential of LLMs for practical application in detecting anti-LGBTQIA+ user-generated texts and provides valuable insights from text analysis that can inform topic modelling. These findings contribute to developing safer digital platforms and enhancing protection for LGBTQIA+ individuals."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nguyen-etal-2025-leveraging">
<titleInfo>
<title>Leveraging Large Language Models in Detecting Anti-LGBTQIA+ User-generated Texts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Quoc-Toan</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Josh</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tuan</namePart>
<namePart type="family">Pham</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">William</namePart>
<namePart type="given">John</namePart>
<namePart type="family">Teahan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Queer in AI Workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">A</namePart>
<namePart type="family">Pranav</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alissa</namePart>
<namePart type="family">Valentine</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shaily</namePart>
<namePart type="family">Bhatt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yanan</namePart>
<namePart type="family">Long</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arjun</namePart>
<namePart type="family">Subramonian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amanda</namePart>
<namePart type="family">Bertsch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anne</namePart>
<namePart type="family">Lauscher</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ankush</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hybrid format (in-person and virtual)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-244-2</identifier>
</relatedItem>
<abstract>Anti-LGBTQIA+ texts in user-generated content pose significant risks to online safety and inclusivity. This study investigates the capabilities and limitations of five widely adopted Large Language Models (LLMs)—DeepSeek-V3, GPT-4o, GPT-4o-mini, GPT-o1-mini, and Llama3.3-70B—in detecting such harmful content. Our findings reveal that while LLMs demonstrate potential in identifying offensive language, their effectiveness varies across models and metrics, with notable shortcomings in calibration. Furthermore, linguistic analysis exposes deeply embedded patterns of discrimination, reinforcing the urgency for improved detection mechanisms for this marginalised population. In summary, this study demonstrates the significant potential of LLMs for practical application in detecting anti-LGBTQIA+ user-generated texts and provides valuable insights from text analysis that can inform topic modelling. These findings contribute to developing safer digital platforms and enhancing protection for LGBTQIA+ individuals.</abstract>
<identifier type="citekey">nguyen-etal-2025-leveraging</identifier>
<identifier type="doi">10.18653/v1/2025.queerinai-main.4</identifier>
<location>
<url>https://aclanthology.org/2025.queerinai-main.4/</url>
</location>
<part>
<date>2025-05</date>
<extent unit="page">
<start>26</start>
<end>34</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Leveraging Large Language Models in Detecting Anti-LGBTQIA+ User-generated Texts
%A Nguyen, Quoc-Toan
%A Nguyen, Josh
%A Pham, Tuan
%A Teahan, William John
%Y Pranav, A.
%Y Valentine, Alissa
%Y Bhatt, Shaily
%Y Long, Yanan
%Y Subramonian, Arjun
%Y Bertsch, Amanda
%Y Lauscher, Anne
%Y Gupta, Ankush
%S Proceedings of the Queer in AI Workshop
%D 2025
%8 May
%I Association for Computational Linguistics
%C Hybrid format (in-person and virtual)
%@ 979-8-89176-244-2
%F nguyen-etal-2025-leveraging
%X Anti-LGBTQIA+ texts in user-generated content pose significant risks to online safety and inclusivity. This study investigates the capabilities and limitations of five widely adopted Large Language Models (LLMs)—DeepSeek-V3, GPT-4o, GPT-4o-mini, GPT-o1-mini, and Llama3.3-70B—in detecting such harmful content. Our findings reveal that while LLMs demonstrate potential in identifying offensive language, their effectiveness varies across models and metrics, with notable shortcomings in calibration. Furthermore, linguistic analysis exposes deeply embedded patterns of discrimination, reinforcing the urgency for improved detection mechanisms for this marginalised population. In summary, this study demonstrates the significant potential of LLMs for practical application in detecting anti-LGBTQIA+ user-generated texts and provides valuable insights from text analysis that can inform topic modelling. These findings contribute to developing safer digital platforms and enhancing protection for LGBTQIA+ individuals.
%R 10.18653/v1/2025.queerinai-main.4
%U https://aclanthology.org/2025.queerinai-main.4/
%U https://doi.org/10.18653/v1/2025.queerinai-main.4
%P 26-34
Markdown (Informal)
[Leveraging Large Language Models in Detecting Anti-LGBTQIA+ User-generated Texts](https://aclanthology.org/2025.queerinai-main.4/) (Nguyen et al., QueerInAI 2025)
ACL