@inproceedings{crescenzi-etal-2026-raging,
title = "{RAG}ing Against Misogyny: Improving Implicit Misogyny Explanations",
author = "Crescenzi, Ivana and
Muti, Arianna and
Sap, Maarten and
Caselli, Tommaso and
Nozza, Debora",
editor = "Fale{\'n}ska, Agnieszka and
Basta, Christine and
Costa-juss{\`a}, Marta and
Sta{\'n}czak, Karolina and
Nozza, Debora and
Attanasio, Giuseppe and
Neplenbroek, Vera and
Hardmeier, Christian",
booktitle = "Proceedings of the 7th Workshop on Gender Bias in Natural Language Processing ({G}e{BNLP})",
month = nov,
year = "2026",
address = "Hengqin, China (remote)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.gebnlp-1.8/",
pages = "111--125",
ISBN = "979-8-89176-447-7",
abstract = "Implicit misogyny often requires background knowledge to be understood. To address this challenge, we propose a Retrieval-Augmented Generation (RAG) framework for detecting and explaining implicit misogyny in English and Italian, leveraging encyclopedic, slang, and feminist knowledge sources. Using the ImplicIT-Mis and SBIC+ datasets, we evaluate the contribution of each knowledge source to detection and explanation quality, investigating also whether RAG addresses known LLM failure modes in implicit misogyny. Results show that RAG improves recall on Italian data, but does not improve English detection performance. However, human evaluation shows that RAG-based explanations are preferred over no-RAG explanations in both languages. Feminist literature emerges as the most consistently useful source for detection and explanation."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="crescenzi-etal-2026-raging">
<titleInfo>
<title>RAGing Against Misogyny: Improving Implicit Misogyny Explanations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ivana</namePart>
<namePart type="family">Crescenzi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arianna</namePart>
<namePart type="family">Muti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maarten</namePart>
<namePart type="family">Sap</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tommaso</namePart>
<namePart type="family">Caselli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Debora</namePart>
<namePart type="family">Nozza</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 7th Workshop on Gender Bias in Natural Language Processing (GeBNLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Agnieszka</namePart>
<namePart type="family">Faleńska</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christine</namePart>
<namePart type="family">Basta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marta</namePart>
<namePart type="family">Costa-jussà</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Karolina</namePart>
<namePart type="family">Stańczak</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">Giuseppe</namePart>
<namePart type="family">Attanasio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vera</namePart>
<namePart type="family">Neplenbroek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christian</namePart>
<namePart type="family">Hardmeier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hengqin, China (remote)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-447-7</identifier>
</relatedItem>
<abstract>Implicit misogyny often requires background knowledge to be understood. To address this challenge, we propose a Retrieval-Augmented Generation (RAG) framework for detecting and explaining implicit misogyny in English and Italian, leveraging encyclopedic, slang, and feminist knowledge sources. Using the ImplicIT-Mis and SBIC+ datasets, we evaluate the contribution of each knowledge source to detection and explanation quality, investigating also whether RAG addresses known LLM failure modes in implicit misogyny. Results show that RAG improves recall on Italian data, but does not improve English detection performance. However, human evaluation shows that RAG-based explanations are preferred over no-RAG explanations in both languages. Feminist literature emerges as the most consistently useful source for detection and explanation.</abstract>
<identifier type="citekey">crescenzi-etal-2026-raging</identifier>
<location>
<url>https://aclanthology.org/2026.gebnlp-1.8/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>111</start>
<end>125</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T RAGing Against Misogyny: Improving Implicit Misogyny Explanations
%A Crescenzi, Ivana
%A Muti, Arianna
%A Sap, Maarten
%A Caselli, Tommaso
%A Nozza, Debora
%Y Faleńska, Agnieszka
%Y Basta, Christine
%Y Costa-jussà, Marta
%Y Stańczak, Karolina
%Y Nozza, Debora
%Y Attanasio, Giuseppe
%Y Neplenbroek, Vera
%Y Hardmeier, Christian
%S Proceedings of the 7th Workshop on Gender Bias in Natural Language Processing (GeBNLP)
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, China (remote)
%@ 979-8-89176-447-7
%F crescenzi-etal-2026-raging
%X Implicit misogyny often requires background knowledge to be understood. To address this challenge, we propose a Retrieval-Augmented Generation (RAG) framework for detecting and explaining implicit misogyny in English and Italian, leveraging encyclopedic, slang, and feminist knowledge sources. Using the ImplicIT-Mis and SBIC+ datasets, we evaluate the contribution of each knowledge source to detection and explanation quality, investigating also whether RAG addresses known LLM failure modes in implicit misogyny. Results show that RAG improves recall on Italian data, but does not improve English detection performance. However, human evaluation shows that RAG-based explanations are preferred over no-RAG explanations in both languages. Feminist literature emerges as the most consistently useful source for detection and explanation.
%U https://aclanthology.org/2026.gebnlp-1.8/
%P 111-125
Markdown (Informal)
[RAGing Against Misogyny: Improving Implicit Misogyny Explanations](https://aclanthology.org/2026.gebnlp-1.8/) (Crescenzi et al., GeBNLP 2026)
ACL
- Ivana Crescenzi, Arianna Muti, Maarten Sap, Tommaso Caselli, and Debora Nozza. 2026. RAGing Against Misogyny: Improving Implicit Misogyny Explanations. In Proceedings of the 7th Workshop on Gender Bias in Natural Language Processing (GeBNLP), pages 111–125, Hengqin, China (remote). Association for Computational Linguistics.