From Language to Action in Arabic: Reliable Structured Tool Calling via Data-Centric Fine-Tuning
Function-calling language models are essential for agentic AI systems that translate natural language into executable structured actions, yet existing models exhibit severe structural instability when applied to Arabic. We present AISA-AR-FunctionCall, a production-oriented Arabic function-calling framework built on a 270M-parameter FunctionGemma backbone and trained through systematic dataset auditing, schema repair, tool-aware prompt restructuring, and full-parameter supervised fine-tuning. On a held-out test set, fine-tuning reduces parse failures from 87\% to below 1\%, improves function name accuracy by more than eightfold, and substantially enhances argument alignment across dialect...
| Authors | Omer Nacar, Deema Alquffari, Saleh Alsharideh et al. |
|---|---|
| Primary category | cs.LG |
| Published | 4 March 2026 |
| Last updated at source | 4 March 2026 |
Connected in the knowledge graph
- TuwaiqAcademy/AISA-ArabicFCDataset · cited by
Models and datasets referencing this paper
- TuwaiqAcademy/AISA-ArabicFCDataset
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.