PuDyDG at AISA-ArabicFC: Decomposed Fine-Tuning with Function-Centric Few-Shot Augmentation for Arabic Function Calling
Year: 2026
Type: conference-paper
Abstract: Tool calling has become increasingly important for agentic systems, but remains challenging in multilingual settings, particularly for Arabic.We present our system for the AISA-ArabicFC shared task at ArabicNLP 2026.Our approach combines decomposed multi-task fine-tuning, function-centric few-shot augmentation, and hybrid schema-aware inference.On the development set, our system achieves a functionname accuracy of 1.000 and a normalized argument exact match of 0.858.On the blind test set, the released baseline re-scored with the final scorer obtains a Track A score of 0.8000, compared with 0.9111 for our submission.Our system achieves a function-name accuracy of 0.9973 and an argument exact match score of 0.8536 on this set, ranking seventh in Track A. Our solution is released in the GitHub repository 1 .
Authors: Duy Dang Phu, Thìn Đặng Văn
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: bronze
OpenAlex ID: W7224439617