Metraipolis › archive › dc_4f863bbf82ce

Lost in Translation: Measuring the Effect of Non-Native English on End User Performance of Large Language Models — arXiv:2609.36214

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.36214
License (as archived)
CC0-1.0
Archived
2026-10-07T16:56:27.321Z
SHA-256 of the archived text
98d1df90474aec8637cd68ab55de60226437db25ff0856325cc96898c3a139e5
Stable URL of this page
https://metraipolis.com/documento/dc_4f863bbf82ce

How to cite

Lost in Translation: Measuring the Effect of Non-Native English on End User Performance of Large Language Models — arXiv:2609.36214 — arXiv (en), https://arxiv.org/abs/2609.36214 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4f863bbf82ce (Metraipolis archive dc_4f863bbf82ce, sha256 98d1df90474aec8637cd68ab55de60226437db25ff0856325cc96898c3a139e5)
BibTeX
@misc{dc4f863bbf82ce,
  title = {Lost in Translation: Measuring the Effect of Non-Native English on End User Performance of Large Language Models — arXiv:2609.36214},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.36214},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4f863bbf82ce; sha256 98d1df90474aec8637cd68ab55de60226437db25ff0856325cc96898c3a139e5},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.36214. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large language models (LLMs) are increasingly used by people whose first language is not English, yet these users have been shown to receive systematically lower-quality responses than fluent speakers. Which specific features of non-native English drive this gap remains unclear, because fluency is itself a composite of mechanical accuracy, vocabulary use, organization, and discourse coherence. Here, we introduce FABLE, a controlled dataset of 190,911 English prompt variants derived from 174K real user prompts for writing-related tasks. Evaluating responses from 34 open-weight LLMs, we find a clear asymmetry; while models do not propagate surface errors such as misspellings into their outputs, models do mirror higher-level rhetorical and lexical qualities present in the user's prompt. Further, the overall quality of responses differs substantially between the least- and most-fluent prompts. These results highlight a key LLM performance disparity for non-native English LLM users, resulting in both lower-quality and less-fluent answers.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-30 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2609.36214 — 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 2026-10-07T16:27:03.191Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).