Ivana Crescenzi
Author directory2026
RAGing Against Misogyny: Improving Implicit Misogyny Explanations
Ivana Crescenzi | Arianna Muti | Maarten Sap | Tommaso Caselli | Debora Nozza
Proceedings of the 7th Workshop on Gender Bias in Natural Language Processing (GeBNLP)
Ivana Crescenzi | Arianna Muti | Maarten Sap | Tommaso Caselli | Debora Nozza
Proceedings of the 7th Workshop on Gender Bias in Natural Language Processing (GeBNLP)
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.
Search