arXiv AI
When Does Hate Transfer? A Large-Scale Study of Cross-Lingual Hate Speech Detection
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Aug 28
Training-Time Explainability for Multilingual Hate Speech Detection: Aligning Model Reasoning with Human Rationales
The paper proposes a training‑time explainability framework that aligns model reasoning with human‑annotated rationales to improve both classification performance and interpretability for multilingual hate speech detection. It is evaluated on HateXplain (English) and BullySent (Hinglish), datasets that capture anti‑Muslim hate in culturally coded, multilingual forms. Using methods such as LIME, Integrated Gradients, Grad‑X‑Input, and attention, the study shows that gradient‑ and attention‑based regularization boosts F‑scores, enhances plausibility and faithfulness, and captures culturally specific cues for detecting implicit anti‑Muslim hate.
arXiv AI
Aug 25
SPAR-Hate: An Auditor-Guided Multi-Agent Framework for Bilingual Hate Speech Parsing
arXiv:2608.22018v1 Announce Type: new Abstract: Hate speech detection has recently shifted from coarse-grained classification to structured parsing, where systems must jointly identify hateful target...
arXiv Computation and Language
Oct 15
From Triage to Impact: A Multi-Hop Reasoning Benchmark for Explainable Persian Hate Speech
arXiv:2610.20370v1 Announce Type: new Abstract: Hate speech has become increasingly prevalent on social media, raising concerns about its detection, interpretation, and moderation. Persian, a relativ...
arXiv Computation and Language
Sep 16
ParsHate: A Benchmark Dataset for Hate and Target Detection in Persian
arXiv:2609.16393v1 Announce Type: new Abstract: We introduce ParsHate, a manually annotated dataset of 10,000 Persian tweets spanning 2013-2022, representing the first decade-long benchmark for hate...
Hugging Face Trending Papers
Sep 14
ParsHate: A Benchmark Dataset for Hate and Target Detection in Persian
We introduce ParsHate, a manually annotated dataset of 10,000 Persian tweets spanning 2013-2022, representing the first decade-long benchmark for hate speech detection in Persian. The dataset contains...
arXiv Computation and Language
Sep 28
MexHat: A Dataset for Hate Speech Detection in Mexican Spanish Videos
MexHat is a newly released video dataset aimed at improving hate‑speech detection in Mexican Spanish. It contains roughly 1,000 clips annotated for three broad categories—no negative content, offensive content, and hate‑speech—as well as a finer classification into three hate‑speech sub‑categories. The paper presents dataset statistics and baseline results, underscoring the challenges of detecting culturally and contextually nuanced hate speech in multimodal content.