<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mnassri-etal-2025-rag">
    <titleInfo>
        <title>RAG and Recall: Multilingual Hate Speech Detection with Semantic Memory</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Khouloud</namePart>
        <namePart type="family">Mnassri</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Reza</namePart>
        <namePart type="family">Farahbakhsh</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Noel</namePart>
        <namePart type="family">Crespi</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>Multilingual hate speech detection presents a challenging task, particularly in limited-resource contexts when performance is affected by cultural nuances and data scarcity. Fine-tuned models are often unable to generalize beyond their training, which limits their efficiency, especially for low-resource languages. In this paper, we introduce HS-RAG, a retrieval-augmented generation (RAG) system that directly leverages knowledge, in English, French, and Arabic, from Hate Speech Superset (publicly available dataset) and Wikipedia to Large Language Models (LLMs). To further enhance robustness, we introduce HS-MemRAG, a memory-augmented extension that integrates a semantic cache. This model reduces redundant retrieval while improving contextual relevance and hate speech detection among the three languages.</abstract>
    <identifier type="citekey">mnassri-etal-2025-rag</identifier>
    <location>
        <url>https://aclanthology.org/2025.woah-1.20/</url>
    </location>
    <part>
        <date>2025-08</date>
        <extent unit="page">
            <start>219</start>
            <end>227</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T RAG and Recall: Multilingual Hate Speech Detection with Semantic Memory
%A Mnassri, Khouloud
%A Farahbakhsh, Reza
%A Crespi, Noel
%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 mnassri-etal-2025-rag
%X Multilingual hate speech detection presents a challenging task, particularly in limited-resource contexts when performance is affected by cultural nuances and data scarcity. Fine-tuned models are often unable to generalize beyond their training, which limits their efficiency, especially for low-resource languages. In this paper, we introduce HS-RAG, a retrieval-augmented generation (RAG) system that directly leverages knowledge, in English, French, and Arabic, from Hate Speech Superset (publicly available dataset) and Wikipedia to Large Language Models (LLMs). To further enhance robustness, we introduce HS-MemRAG, a memory-augmented extension that integrates a semantic cache. This model reduces redundant retrieval while improving contextual relevance and hate speech detection among the three languages.
%U https://aclanthology.org/2025.woah-1.20/
%P 219-227

Markdown (Informal)

[RAG and Recall: Multilingual Hate Speech Detection with Semantic Memory](https://aclanthology.org/2025.woah-1.20/) (Mnassri et al., WOAH 2025)

• RAG and Recall: Multilingual Hate Speech Detection with Semantic Memory (Mnassri et al., WOAH 2025)

ACL

• Khouloud Mnassri, Reza Farahbakhsh, and Noel Crespi. 2025. RAG and Recall: Multilingual Hate Speech Detection with Semantic Memory. In Proceedings of the The 9th Workshop on Online Abuse and Harms (WOAH), pages 219–227, Vienna, Austria. Association for Computational Linguistics.