Metraipolis › archive › dc_d80192948ce2

YallaMorph: A Benchmark for Evaluating Arabic Morphological Generation in Large Language Models — arXiv:2609.10153

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.10153
License (as archived)
CC0-1.0
Archived
2026-10-16T07:53:26.464Z
SHA-256 of the archived text
23582a3fd6637b85168a050308463f1ce65c1426a3d7fcd7cae46ba450411436
Stable URL of this page
https://metraipolis.com/documento/dc_d80192948ce2

How to cite

YallaMorph: A Benchmark for Evaluating Arabic Morphological Generation in Large Language Models — arXiv:2609.10153 — arXiv (en), https://arxiv.org/abs/2609.10153 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d80192948ce2 (Metraipolis archive dc_d80192948ce2, sha256 23582a3fd6637b85168a050308463f1ce65c1426a3d7fcd7cae46ba450411436)
BibTeX
@misc{dcd80192948ce2,
  title = {YallaMorph: A Benchmark for Evaluating Arabic Morphological Generation in Large Language Models — arXiv:2609.10153},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.10153},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d80192948ce2; sha256 23582a3fd6637b85168a050308463f1ce65c1426a3d7fcd7cae46ba450411436},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.10153. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Arabic morphology remains challenging for large language models, since fluent generation does not guarantee accurate morphosyntactic control. Existing Arabic evaluations mainly target downstream tasks and do not directly test controlled morphological generation from explicit lexical and feature-based input. We introduce YallaMorph, a large-scale benchmark for Arabic morphological generation covering verbs, nouns, adjectives, their cliticized forms, and invalid configurations. We evaluate multilingual and Arabic-oriented LLMs under diacritized and undiacritized settings over 600K benchmark entries. Results show that Arabic morphological generation remains difficult, especially for cliticized, unseen, and morphologically rare forms.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-10 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2609.10153 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-16T07:24:00.924Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-10?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).