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).
Both submissions use one backbone -- JAIS-6.7B fine-tuned with 4-bit QLoRA and a linear classification head over its last-token representation.
Task B1: Binary Safe/Unsafe
For B1 we train a four-way head that factors the label by dialect register {safe, unsafe} x {MSA, other}, we augment the training fold with MSA prompts from AraSafe, and decode with a plain argmax to score safe/unsafe.
Task B2: Seven-Way Harm Domain
For B2 we fine-tune the same backbone as a seven-way classifier and average the softmax outputs of five random seeds.
Results
- Both submissions ranked first on their track, with macro-F1 0.984 on B1 and 0.790 on B2.
- On B1, the model is accurate across all six dialects (93.6--99.8%) and its predicted unsafe rate tracks the true rate closely.
- On B2, six of the seven classes reach F1 between 0.73 and 0.98, with the residual error concentrated in the Bully class, which overlaps semantically with harassment and harm-to-others.