Skip to content
conftrace_
2026 EMNLP EMNLP 2026

Arabic Morphosyntactic Tagging and Dependency Parsing with Large Language Models

AbstractLLMs perform strongly across NLP, but their ability to produce explicit grammatical analyses remains unclear. Arabic provides a challenging testbed due to its rich morphology and orthographic ambiguity, which create strong morphology–syntax interactions. We present a unified evaluation of LLMs on Arabic morphosyntactic tagging and dependency parsing, covering pre-tokenized, raw-text, and cascaded settings. We compare zero-shot prompting with retrieval-based in-context learning. Relevant demonstrations substantially improve performance. The strongest LLMs approach supervised tagging and parsing systems; however, they require substantial annotated data for demonstration retrieval and considerable computational resources. We make all code and data used in this paper publicly available.

More from EMNLP 2026

All EMNLP 2026 papers →