New on preventhate.org, 16 October 2025 (Policyinstitute.net)
(Gemini Audio) preventhate.org | Policyinstitute.net
Multi3Hate: Multimodal, Multilingual, and Multicultural Hate Speech Detection with Vision–Language Models (ACL Anthology)
Multimodal content, linguistic diversity, and cultural perception are the main causes of the difficulties in global hate speech moderation. We…
A Bilingual Malay-English Social Media Dataset for Binary Hate Speech Detection (Data in Brief)
Despite the growing threats to safety and unity posed by online hate speech, Southeast Asian languages, such as Malay, are…
Bridging Gaps in Hate Speech Detection: Meta-Collections and Benchmarks for Low-Resource Iberian Languages (arXiv)
Research on hate speech identification is still primarily focused on English, which hinders advancements for low-resource languages with a wide…
Two Weeks in Soft Security: Free Resources on Countering Extremism, Hate, and Disinformation, September 2025 (II/II)
Browse and read from a list of the 180 most popular LinkedIn resources dealing with soft counter-extremism, countering hate speech,…
DeHate: A Stable Diffusion-based Multimodal Approach to Mitigate Hate Speech in Images (arXiv)
In addition to distorting public discourse, the proliferation of harmful online information presents serious obstacles to preserving a safe digital…
Relieving Bias in Hate Speech Detection with a Small Number of Expert Annotations: A Prompt-based Learning Approach (SSRN)
The research at hand tackles bias in automatic hate speech detection on social media, where linguistic heterogeneity within speaker groups…
SMARTER: A Data-efficient Framework to Improve Toxicity Detection with Explanation via Self-augmenting Large Language Models (arXiv)
The researchers provide SMARTER, a two-stage paradigm for explainable content moderation that uses Large Language Models (LLMs) and is data-efficient.…
AI-driven detection of hate speech on social media: a case study in the French language (HomeCluster Computing)
The understudied field of hate speech identification in French-language social media, where platform ubiquity and user anonymity have increased the…
A Robust and Linguistically-Aware Hate Speech Detection System for Roman Urdu (ACM Digital Library)
The current study presents a comprehensive approach to detecting hate speech in Roman Urdu, a widely used but under-resourced language…
Two Weeks in Soft Security: Free Resources on Countering Extremism, Hate, and Disinformation, September 2025 (I/II)
Browse and read from a list of the 160 most popular LinkedIn resources dealing with soft counter-extremism, countering hate speech,…
A Vision-Language Model for Multitask Classification of Memes (Neural Networks)
The current study tackles the challenges of multimodal hate speech identification in internet memes, which frequently combine text and images…