홈 › Papers

From Language to Action in Arabic: Reliable Structured Tool Calling via Data-Centric Fine-Tuning

2026-03-04 · Omer Nacar, Deema Alquffari, Saleh Alsharideh, Adeem AlOtaibi, Abdulaziz Alabdulkarim, Leen Alhazmi, Nada Alomar, Wareef Alzubaidi, Nada Alsultan, Ahmed Alrabghi, Demah Alhoshan, Rana Alsayyari, Hamed Alruwaili, Albaraa Jaafar, Khaled Alusmani, Abdulaziz Alsohimy, Munirah Alsubaie, Shahd Aldukhayil, Arwa Alali, Yazeed BinShihah, Razan Alsulaymi, Nourah Alhumaid, Razan Abdulsalam, Reem Alamoudi, Mohammed Alkhalifa arxiv

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 dialects and domains. Error analysis reveals a transition from structural collapse to semantic misalignment, suggesting that serialization stability and decision-level reasoning are separable challenges. We further explore a reasoning-augmented LoRA variant that introduces explicit intermediate reasoning prior to tool invocation. All datasets and models are publicly released under the AISA framework.

📄 PDF Abstract BibTeX arXiv:2603.16901

Code (0)

등록된 구현이 없습니다.

Arabic Prompts with English Tools: A Benchmark

2026-01-08 · Konstantin Kubrak, Ahmed El-Moselhy, Ammar Alsulami, Remaz Altuwaim 외 arxiv

Large Language Models (LLMs) are now integral to numerous industries, increasingly serving as the core reasoning engine for autonomous agents that perform complex tasks through tool-use. While the development of Arabic-n…

Evaluation of Small Language Models for Arabic Language Processing

2026-06-19 · Jumana Alsubhi, Ahmed Alhusayni, Abdulrahman Gharawi, Israa Hamdine 외 arxiv

This paper evaluates the performance of twelve Small Language Models (SLMs) on Arabic natural language processing tasks. The study introduces a benchmark of 240 Arabic test items distributed across eight domains and ten …

VQA support to Arabic Language Learning Educational Tool

2025-08-05 · Khaled Bachir Delassi, Lakhdar Zeggane, Hadda Cherroun, Abdelhamid Haouhat 외 arxiv

We address the problem of scarcity of educational Arabic Language Learning tools that advocate modern pedagogical models such as active learning which ensures language proficiency. In fact, we investigate the design and …

Visual Question Answering Active Learning

ArabicNumBench: Evaluating Arabic Number Reading in Large Language Models

2026-02-21 · Anas Alhumud, Abdulaziz Alhammadi, Muhammad Badruddin Khan arxiv

We present ArabicNumBench, a comprehensive benchmark for evaluating large language models on Arabic number reading tasks across Eastern Arabic-Indic numerals (0-9 in Arabic script) and Western Arabic numerals (0-9). We e…

Arabic Data Science Toolkit: An API for Arabic Language Feature Extraction

2018-05-01 · LREC 2018 5 · Paul Rodrigues, Valerie Novak, C. Anton Rytting, Julie Yelle 외