We describe the QMUL_AK submission to AISA-ArabicFC 2026. The system adapts the Arabic-English ALLaM-7B-Instruct model to function calling with low-rank adaptation (LoRA). The same output supports Track A function calling and Track B reasoning-augmented calling. Training uses only the official task data.
Methodology
It combines:
- an Arabic schema-aware prompt,
- dialect and no-call resampling,
- a token-weighted training objective, and
- deterministic validation of generated calls against the candidate tool schema.
Results
On the development set, the system achieves 0.9982 function accuracy and 0.8920 argument exact match,