QMUL AK at AISA-ArabicFC: Schema-Constrained Function Calling with ALLaM
cs.CL
Submitted: 2026-10-27
Updated: 2026-10-27
Comments: Published at ArabicNLP 2026 (Shared Tasks), co-located with EMNLP 2026. ACL Anthology: https://aclanthology.org/2026.arabicnlp-sharedtasks.203/
Journal ref: Proceedings of The Fourth Arabic Natural Language Processing Conference: Shared Tasks, pages 1580-1584 (2026)
License: http://creativecommons.org/licenses/by/4.0/
The gist: We describe the QMUL AK submission to AISA-ArabicFC 2026.
Abstract
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). 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. The same output supports Track A function calling and Track B reasoning-augmented calling. Training uses only the official task data. On the development set, the system achieves 0.9982 function accuracy and 0.8920 argument exact match, corresponding to overall A and B scores of 0.9345 and 0.9454. On the blind test set, the system reaches overall A and B scores of 0.9253 and 0.9380, ranking 3rd on both submission tracks and 1st of 21 teams on the Track C dialect-robustness diagnostic with a macro-averaged score of 0.9075 and the smallest dialect gap in the shared task (0.077). The results show that function selection is nearly saturated, while argument extraction remains the main source of error.
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data