arXiv:2608.21985v1 Announce Type: new
Abstract: As the adoption of large language models (LLMs) grows in Arabic-speaking regions, ensuring their safety and cultural alignment is increasingly critical...
By Fidaa Abed, Haidar Khan, M Saiful Bari, Babar Khan, Abdalghani Abujabal
arXiv:2610.26474v2 Announce Type: replace
Abstract: Large language models (LLMs) designed to interact with users are typically trained to respond appropriately to harmful or toxic content. However, e...
By Israel Abebe Azime, Jesujoba O. Alabi, Iffat Maab, Alexander D. Cai, Tadesse Destaw Belay, Atnafu Lambebo Tonja, Jonas Kgomo, Folasade Alabi, Salomey Osei, Saminu Muhammad Aliyu, Nkechinyere Faith Aguobi, Bontu Fufa Balcha, Blessing Sibanda, Davis David, Mouhamadane Mboup, Daud Abolade, Neo Putini, Louis Powell, Kiant'e Brantley, Philipp Slusallek, Dietrich Klakow, Julia Kreutzer
The paper presents a new taxonomy for online harm on video platforms, expanding existing frameworks to multimodal contexts and defining six content-based categories: Information, Hate and harassment, Addictive, Clickbait, Sexual, and Physical harms. It also evaluates multimodal large language models (MLLMs) as alternative annotators, comparing GPT‑4‑Turbo, non‑trained crowdworkers, and trained human annotators on a dataset of 19,422 potentially harmful YouTube videos. The study finds that MLLMs can perform comparably to human annotators in both binary and multi‑label classification tasks, suggesting potential applications in content moderation and social science research.
By Claire Wonjeong Jo, Miki Weso{\l}owska, Magdalena Wojcieszak
The paper introduces REGLAT, an ensemble-based model that integrates named entity recognition (GLiNER) with a fine‑tuned MARBERT classifier to detect harmful content in Arabic. It classifies user prompts into seven harm categories, achieving a macro‑F1 of 0.886 and accuracy of 0.897 on the ArGuard 2026 development set, with slightly lower scores on blind test sets. The study highlights that combining explicit entity extraction with contextual language modeling improves fine‑grained harmful content detection, though distinguishing closely related categories remains difficult.
By Ahmed M. Fetouh, Mariam Labib, Nsrin Ashraf, Omer Dawood, Hamada Nayel
arXiv:2607. 20447v1 Announce Type: cross Abstract: This paper describes our system for the EEUCA 2026 Shared Task on toxicity classification in gaming chat.
By Anmol Guragain, Marcos Estecha-Garitagoitia, Luis Fernando D'Haro Enr\'iquez, Ricardo de C\'ordoba
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.
By Muhammad Deedahwar Mazhar Qureshi, Sannaan Khan, Muhammad Atif Qureshi, Wael Rashwan