Evaluation of Small Language Models for Arabic Language Processing

• URL: http://arxiv.org/abs/2606.21460v1
• Date: Fri, 19 Jun 2026 14:16:13 GMT
• Title: Evaluation of Small Language Models for Arabic Language Processing
• Abstract summary: The study introduces a benchmark of 240 Arabic test items distributed across eight domains and ten language skills.<n>All models were evaluated under a controlled zero-shot setting using a standardized Arabic-only prompt template.<n>Models with stronger Arabic alignment and more reliable instruction-following behavior tended to perform better across tasks.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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 language skills, covering both comprehension-oriented and generation-oriented tasks. All models were evaluated under a controlled zero-shot setting using a standardized Arabic-only prompt template. Model responses were assessed through a multi-model LLM-as-a-judge framework involving GPT-4.1 Mini, Claude Haiku 4.5, and DeepSeek-Chat, with scores aggregated across judges and analyzed by task, skill, and model family. The results show that Gemma 3 (12B) achieved the highest overall score (4.548/5), followed by Aya and C4AI Command Arabic. The observed results suggest that model size alone does not explain Arabic SLM performance. Models with stronger Arabic alignment and more reliable instruction-following behavior tended to perform better across tasks. Common failure patterns among lower-performing models include prompt leakage, hallucination, language drift, incomplete generation, and weak task adherence. Overall, the benchmark provides a structured reference for evaluating compact Arabic language models and supports future work on efficient, reliable, and culturally appropriate Arabic AI systems.

Related papers

• Evaluating Modern Large Language Models on Low-Resource and Morphologically Rich Languages:A Cross-Lingual Benchmark Across Cantonese, Japanese, and Turkish [12.286855282078305]
  GPT-4o, GPT-4, Claude3.5Sonnet, LLaMA3.1, MistralLarge2, LLaMA-2Chat13B, and Mistral7BInstruct are evaluated.<n>Our benchmark spans four diverse tasks: open-domain question answering, document summarization, English-to-X translation, and culturally grounded dialogue.
  arXiv  Detail & Related papers  (2025-11-05T22:09:53Z)
• Hala Technical Report: Building Arabic-Centric Instruction & Translation Models at Scale [51.41777906371754]
  We present Hala, a family of Arabic-centric instruction and translation models built with our translate-and-tune pipeline.<n>A lightweight language model LFM2-1.2B is then fine-tuned on this data and used to translate high-quality English instruction sets into Arabic.<n>We train Hala models at 350M, 700M, 1.2B, and 9B parameters, and apply slerp merging to balance Arabic specialization with base-model strengths.
  arXiv  Detail & Related papers  (2025-09-17T14:19:28Z)
• Advancing Dialectal Arabic to Modern Standard Arabic Machine Translation [22.369277951685234]
  This paper presents two core contributions to advancing DA-MSA translation for the Levantine, Egyptian, and Gulf dialects.<n>Few-shot prompting consistently outperformed zero-shot, chain-of-thought, and our proposed Ara-TEaR method.<n>For fine-tuning LLMs, a quantized Gemma2-9B model achieved a chrF++ score of 49.88, outperforming zero-shot GPT-4o (44.58)
  arXiv  Detail & Related papers  (2025-07-27T14:37:53Z)
• How well can LLMs Grade Essays in Arabic? [3.101490720236325]
  This research assesses the effectiveness of large language models (LLMs) in the task of Arabic automated essay scoring (AES) using the AR-AES dataset.<n>It explores various evaluation methodologies, including zero-shot, few-shot in-context learning, and fine-tuning.<n>A mixed-language prompting strategy, integrating English prompts with Arabic content, was implemented to improve model comprehension and performance.
  arXiv  Detail & Related papers  (2025-01-27T21:30:02Z)
• ArabicMMLU: Assessing Massive Multitask Language Understanding in Arabic [51.922112625469836]
  We present datasetname, the first multi-task language understanding benchmark for the Arabic language. Our data comprises 40 tasks and 14,575 multiple-choice questions in Modern Standard Arabic (MSA) and is carefully constructed by collaborating with native speakers in the region. Our evaluations of 35 models reveal substantial room for improvement, particularly among the best open-source models.
  arXiv  Detail & Related papers  (2024-02-20T09:07:41Z)
• Beyond English: Evaluating LLMs for Arabic Grammatical Error Correction [19.970419667319046]
  Large language models (LLMs) finetuned to follow human instruction have exhibited significant capabilities in English NLP tasks. We evaluate the abilities of instruction finetuned LLMs in Arabic grammatical error correction (GEC) We find that instruction finetuned models, regardless of their size, are still outperformed by fully finetuned ones, even if they are significantly smaller in size.
  arXiv  Detail & Related papers  (2023-12-13T05:33:25Z)
• AceGPT, Localizing Large Language Models in Arabic [73.39989503874634]
  The paper proposes a comprehensive solution that includes pre-training with Arabic texts, Supervised Fine-Tuning (SFT) utilizing native Arabic instructions, and GPT-4 responses in Arabic. The goal is to cultivate culturally cognizant and value-aligned Arabic LLMs capable of accommodating the diverse, application-specific needs of Arabic-speaking communities.
  arXiv  Detail & Related papers  (2023-09-21T13:20:13Z)
• ChatGPT for Arabic Grammatical Error Correction [5.945320097465418]
  Large language models (LLMs) fine-tuned to follow human instruction have exhibited significant capabilities in English NLP tasks. In this paper, we delve into abilities of instruction fine-tuned LLMs in Arabic GEC, a task made complex due to Arabic's rich morphology. We find that instruction fine-tuned models, regardless of their size, significantly underperform compared to fully fine-tuned models of significantly smaller sizes.
  arXiv  Detail & Related papers  (2023-08-08T18:00:39Z)
• mFACE: Multilingual Summarization with Factual Consistency Evaluation [79.60172087719356]
  Abstractive summarization has enjoyed renewed interest in recent years, thanks to pre-trained language models and the availability of large-scale datasets. Despite promising results, current models still suffer from generating factually inconsistent summaries. We leverage factual consistency evaluation models to improve multilingual summarization.
  arXiv  Detail & Related papers  (2022-12-20T19:52:41Z)
• Few-shot Learning with Multilingual Language Models [66.49496434282564]
  We train multilingual autoregressive language models on a balanced corpus covering a diverse set of languages. Our largest model sets new state of the art in few-shot learning in more than 20 representative languages. We present a detailed analysis of where the model succeeds and fails, showing in particular that it enables cross-lingual in-context learning.
  arXiv  Detail & Related papers  (2021-12-20T16:52:35Z)
• Harnessing Multilinguality in Unsupervised Machine Translation for Rare Languages [48.28540903568198]
  We show that multilinguality is critical to making unsupervised systems practical for low-resource settings. We present a single model for 5 low-resource languages (Gujarati, Kazakh, Nepali, Sinhala, and Turkish) to and from English directions. We outperform all current state-of-the-art unsupervised baselines for these languages, achieving gains of up to 14.4 BLEU.
  arXiv  Detail & Related papers  (2020-09-23T15:07:33Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.