Research

Paper

AI LLM March 17, 2026

Arabic Morphosyntactic Tagging and Dependency Parsing with Large Language Models

Authors

Mohamed Adel, Bashar Alhafni, Nizar Habash

Abstract

Large language models (LLMs) perform strongly on many NLP tasks, but their ability to produce explicit linguistic structure remains unclear. We evaluate instruction-tuned LLMs on two structured prediction tasks for Standard Arabic: morphosyntactic tagging and labeled dependency parsing. Arabic provides a challenging testbed due to its rich morphology and orthographic ambiguity, which create strong morphology-syntax interactions. We compare zero-shot prompting with retrieval-based in-context learning (ICL) using examples from Arabic treebanks. Results show that prompt design and demonstration selection strongly affect performance: proprietary models approach supervised baselines for feature-level tagging and become competitive with specialized dependency parsers. In raw-text settings, tokenization remains challenging, though retrieval-based ICL improves both parsing and tokenization. Our analysis highlights which aspects of Arabic morphosyntax and syntax LLMs capture reliably and which remain difficult.

Metadata

arXiv ID: 2603.16718
Provider: ARXIV
Primary Category: cs.CL
Published: 2026-03-17
Fetched: 2026-03-18 06:02

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.16718v1</id>\n    <title>Arabic Morphosyntactic Tagging and Dependency Parsing with Large Language Models</title>\n    <updated>2026-03-17T16:06:29Z</updated>\n    <link href='https://arxiv.org/abs/2603.16718v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.16718v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Large language models (LLMs) perform strongly on many NLP tasks, but their ability to produce explicit linguistic structure remains unclear. We evaluate instruction-tuned LLMs on two structured prediction tasks for Standard Arabic: morphosyntactic tagging and labeled dependency parsing. Arabic provides a challenging testbed due to its rich morphology and orthographic ambiguity, which create strong morphology-syntax interactions. We compare zero-shot prompting with retrieval-based in-context learning (ICL) using examples from Arabic treebanks. Results show that prompt design and demonstration selection strongly affect performance: proprietary models approach supervised baselines for feature-level tagging and become competitive with specialized dependency parsers. In raw-text settings, tokenization remains challenging, though retrieval-based ICL improves both parsing and tokenization. Our analysis highlights which aspects of Arabic morphosyntax and syntax LLMs capture reliably and which remain difficult.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.CL'/>\n    <published>2026-03-17T16:06:29Z</published>\n    <arxiv:primary_category term='cs.CL'/>\n    <author>\n      <name>Mohamed Adel</name>\n    </author>\n    <author>\n      <name>Bashar Alhafni</name>\n    </author>\n    <author>\n      <name>Nizar Habash</name>\n    </author>\n  </entry>"
}