AraLingBench A Human-Annotated Benchmark for Evaluating Arabic Linguistic Capabilities of Large Language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zbeeb, Mohammad, Hammoud, Hasan Abed Al Kader, Mukalled, Sina, Rizk, Nadine, Karnib, Fatima, Lakkis, Issam, Mohanna, Ammar, Ghanem, Bernard
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918239529861120
author Zbeeb, Mohammad
Hammoud, Hasan Abed Al Kader
Mukalled, Sina
Rizk, Nadine
Karnib, Fatima
Lakkis, Issam
Mohanna, Ammar
Ghanem, Bernard
author_facet Zbeeb, Mohammad
Hammoud, Hasan Abed Al Kader
Mukalled, Sina
Rizk, Nadine
Karnib, Fatima
Lakkis, Issam
Mohanna, Ammar
Ghanem, Bernard
contents We present AraLingBench: a fully human annotated benchmark for evaluating the Arabic linguistic competence of large language models (LLMs). The benchmark spans five core categories: grammar, morphology, spelling, reading comprehension, and syntax, through 150 expert-designed multiple choice questions that directly assess structural language understanding. Evaluating 35 Arabic and bilingual LLMs reveals that current models demonstrate strong surface level proficiency but struggle with deeper grammatical and syntactic reasoning. AraLingBench highlights a persistent gap between high scores on knowledge-based benchmarks and true linguistic mastery, showing that many models succeed through memorization or pattern recognition rather than authentic comprehension. By isolating and measuring fundamental linguistic skills, AraLingBench provides a diagnostic framework for developing Arabic LLMs. The full evaluation code is publicly available on GitHub.
format Preprint
id arxiv_https___arxiv_org_abs_2511_14295
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle AraLingBench A Human-Annotated Benchmark for Evaluating Arabic Linguistic Capabilities of Large Language Models
Zbeeb, Mohammad
Hammoud, Hasan Abed Al Kader
Mukalled, Sina
Rizk, Nadine
Karnib, Fatima
Lakkis, Issam
Mohanna, Ammar
Ghanem, Bernard
Computation and Language
Artificial Intelligence
Machine Learning
We present AraLingBench: a fully human annotated benchmark for evaluating the Arabic linguistic competence of large language models (LLMs). The benchmark spans five core categories: grammar, morphology, spelling, reading comprehension, and syntax, through 150 expert-designed multiple choice questions that directly assess structural language understanding. Evaluating 35 Arabic and bilingual LLMs reveals that current models demonstrate strong surface level proficiency but struggle with deeper grammatical and syntactic reasoning. AraLingBench highlights a persistent gap between high scores on knowledge-based benchmarks and true linguistic mastery, showing that many models succeed through memorization or pattern recognition rather than authentic comprehension. By isolating and measuring fundamental linguistic skills, AraLingBench provides a diagnostic framework for developing Arabic LLMs. The full evaluation code is publicly available on GitHub.
title AraLingBench A Human-Annotated Benchmark for Evaluating Arabic Linguistic Capabilities of Large Language Models
topic Computation and Language
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2511.14295