AI Research
AK_QMUL at ArGuard Shared Tasks: A Single Fine-Tuned JAIS for Arabic Harmful-Prompt Detection
AK_QMUL reports results for binary safety and seven-way harm classification
We present AK_QMUL's submissions to the ArGuard-2026 shared tasks on Arabic harmful-prompt detection: a binary safe/unsafe task (B1) and a seven-way harm-domain task (B2).
AC
ArXiv CS.CL
Source
ArXiv CS.CL
AI Analysis
Generated insight by OnAirToday AI
Arabic harmful-prompt detection involves both identifying whether a prompt is unsafe and classifying its harm domain. The submission examines a single fine-tuned JAIS model across both task types.
Powered by AI • Not a substitute for human analysisMore Insights →
Share
Filed under:AI Research
Comments
Keep comments relevant and respectful. No links, advertising, self-promotion, or spam.