@inproceedings{melis-etal-2025-modular,
title = "A Modular Taxonomy for Hate Speech Definitions and Its Impact on Zero-Shot {LLM} Classification Performance",
author = "Melis, Matteo and
Lapesa, Gabriella and
Assenmacher, Dennis",
editor = "Calabrese, Agostina and
de Kock, Christine and
Nozza, Debora and
Plaza-del-Arco, Flor Miriam and
Talat, Zeerak and
Vargas, Francielle",
booktitle = "Proceedings of the The 9th Workshop on Online Abuse and Harms (WOAH)",
month = aug,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.woah-1.45/",
pages = "490--521",
ISBN = "979-8-89176-105-6",
abstract = "Detecting harmful content is a crucial task in the landscape of NLP applications for Social Good, with hate speech being one of its most dangerous forms. But what do we mean by hate speech, how can we define it and how does prompting different definitions of hate speech affect model performance? The contribution of this work is twofold. At the theoretical level, we address the ambiguity surrounding hate speech by collecting and analyzing existing definitions from the literature. We organize these definitions into a taxonomy of 14 conceptual elements{---}building blocks that capture different aspects of hate speech definitions, such as references to the target of hate. At the experimental level, we employ the collection of definitions in a systematic zero-shot evaluation of three LLMs, on three hate speech datasets representing different types of data (synthetic, human-in-the-loop, and real-world). We find that choosing different definitions, i.e., definitions with a different degree of specificity in terms of encoded elements, impacts model performance, but this effect is not consistent across all architectures."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="melis-etal-2025-modular">
<titleInfo>
<title>A Modular Taxonomy for Hate Speech Definitions and Its Impact on Zero-Shot LLM Classification Performance</title>
</titleInfo>
<name type="personal">
<namePart type="given">Matteo</namePart>
<namePart type="family">Melis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gabriella</namePart>
<namePart type="family">Lapesa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dennis</namePart>
<namePart type="family">Assenmacher</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the The 9th Workshop on Online Abuse and Harms (WOAH)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Agostina</namePart>
<namePart type="family">Calabrese</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christine</namePart>
<namePart type="family">de Kock</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Debora</namePart>
<namePart type="family">Nozza</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Flor</namePart>
<namePart type="given">Miriam</namePart>
<namePart type="family">Plaza-del-Arco</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zeerak</namePart>
<namePart type="family">Talat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francielle</namePart>
<namePart type="family">Vargas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-105-6</identifier>
</relatedItem>
<abstract>Detecting harmful content is a crucial task in the landscape of NLP applications for Social Good, with hate speech being one of its most dangerous forms. But what do we mean by hate speech, how can we define it and how does prompting different definitions of hate speech affect model performance? The contribution of this work is twofold. At the theoretical level, we address the ambiguity surrounding hate speech by collecting and analyzing existing definitions from the literature. We organize these definitions into a taxonomy of 14 conceptual elements—building blocks that capture different aspects of hate speech definitions, such as references to the target of hate. At the experimental level, we employ the collection of definitions in a systematic zero-shot evaluation of three LLMs, on three hate speech datasets representing different types of data (synthetic, human-in-the-loop, and real-world). We find that choosing different definitions, i.e., definitions with a different degree of specificity in terms of encoded elements, impacts model performance, but this effect is not consistent across all architectures.</abstract>
<identifier type="citekey">melis-etal-2025-modular</identifier>
<location>
<url>https://aclanthology.org/2025.woah-1.45/</url>
</location>
<part>
<date>2025-08</date>
<extent unit="page">
<start>490</start>
<end>521</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Modular Taxonomy for Hate Speech Definitions and Its Impact on Zero-Shot LLM Classification Performance
%A Melis, Matteo
%A Lapesa, Gabriella
%A Assenmacher, Dennis
%Y Calabrese, Agostina
%Y de Kock, Christine
%Y Nozza, Debora
%Y Plaza-del-Arco, Flor Miriam
%Y Talat, Zeerak
%Y Vargas, Francielle
%S Proceedings of the The 9th Workshop on Online Abuse and Harms (WOAH)
%D 2025
%8 August
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-105-6
%F melis-etal-2025-modular
%X Detecting harmful content is a crucial task in the landscape of NLP applications for Social Good, with hate speech being one of its most dangerous forms. But what do we mean by hate speech, how can we define it and how does prompting different definitions of hate speech affect model performance? The contribution of this work is twofold. At the theoretical level, we address the ambiguity surrounding hate speech by collecting and analyzing existing definitions from the literature. We organize these definitions into a taxonomy of 14 conceptual elements—building blocks that capture different aspects of hate speech definitions, such as references to the target of hate. At the experimental level, we employ the collection of definitions in a systematic zero-shot evaluation of three LLMs, on three hate speech datasets representing different types of data (synthetic, human-in-the-loop, and real-world). We find that choosing different definitions, i.e., definitions with a different degree of specificity in terms of encoded elements, impacts model performance, but this effect is not consistent across all architectures.
%U https://aclanthology.org/2025.woah-1.45/
%P 490-521
Markdown (Informal)
[A Modular Taxonomy for Hate Speech Definitions and Its Impact on Zero-Shot LLM Classification Performance](https://aclanthology.org/2025.woah-1.45/) (Melis et al., WOAH 2025)
ACL