Metraipolis › archive › dc_5e645eadcc5b

Some Dialects Are More Equal Than Others: Non-Prestigious Arabic Dialectal Bias in LLMs — arXiv:2609.23955

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.23955
License (as archived)
CC0-1.0
Archived
2026-10-09T06:49:59.928Z
SHA-256 of the archived text
58405c240f7a28b93b644af5267f7e4a3fd85db7ad12c0dcc7b78c0ca98bda76
Stable URL of this page
https://metraipolis.com/documento/dc_5e645eadcc5b

How to cite

Some Dialects Are More Equal Than Others: Non-Prestigious Arabic Dialectal Bias in LLMs — arXiv:2609.23955 — arXiv (en), https://arxiv.org/abs/2609.23955 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5e645eadcc5b (Metraipolis archive dc_5e645eadcc5b, sha256 58405c240f7a28b93b644af5267f7e4a3fd85db7ad12c0dcc7b78c0ca98bda76)
BibTeX
@misc{dc5e645eadcc5b,
  title = {Some Dialects Are More Equal Than Others: Non-Prestigious Arabic Dialectal Bias in LLMs — arXiv:2609.23955},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.23955},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5e645eadcc5b; sha256 58405c240f7a28b93b644af5267f7e4a3fd85db7ad12c0dcc7b78c0ca98bda76},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.23955. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Previous work on Egyptian Arabic in NLP has focused largely on the prestigious Cairene Egyptian Arabic (CEA) dialect, resulting in a lack of representation for the less prestigious Sa'idi Egyptian Arabic (SEA) dialect both in LLM and resource development. Does this lack of representation influence an LLM's view of the acceptability of SEA (upstream), and does an upstream bias against SEA lead to worse performance (downstream)? We investigate the upstream effect of SEA dialectal features on LLM preferences in a Targeted Syntactic Evaluation (TSE) task which reveals a significant bias against SEA across multiple LLMs. We then analyze the effect of these same features on downstream model performance on MMLU benchmarks and show that models experience a degradation in performance when presented with SEA. This work highlights the need for further exploration on how sub-dialectal variation impacts language technologies.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-22 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2609.23955 — 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 2026-10-09T06:48:45.019Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).