Metraipolis › archive › dc_81fdee52b590
Beyond "AI Language": The case for the idiolectal nature of LLM output — arXiv:2608.06589
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.06589
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T09:46:45.218Z
- SHA-256 of the archived text
f9a2be6fe3509b3b81bf672b7ac455ca5c0224f1736c9b2316082f6f1f87ba8c- Stable URL of this page
https://metraipolis.com/documento/dc_81fdee52b590
How to cite
Beyond "AI Language": The case for the idiolectal nature of LLM output — arXiv:2608.06589 — arXiv (en), https://arxiv.org/abs/2608.06589 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_81fdee52b590 (Metraipolis archive dc_81fdee52b590, sha256 f9a2be6fe3509b3b81bf672b7ac455ca5c0224f1736c9b2316082f6f1f87ba8c)
BibTeX
@misc{dc81fdee52b590,
title = {Beyond "AI Language": The case for the idiolectal nature of LLM output — arXiv:2608.06589},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.06589},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_81fdee52b590; sha256 f9a2be6fe3509b3b81bf672b7ac455ca5c0224f1736c9b2316082f6f1f87ba8c},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.06589. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
While large language model outputs are frequently analysed as a collective super variety termed "AI language," this chapter argues that this perspective coexists with distinct, model-specific linguistic signatures akin to human idiolects. We analyse two datasets of LLM-generated texts on societal topics: a 2024 corpus of six models (Improta et al. 2024) and a newly generated 2026 corpus using the same prompts featuring six contemporary models. Our findings, utilising computational descriptors and stylometric principal component analysis reveal a generational shift between the style of the 2024 and 2026 cohorts, while demonstrating that each individual model maintains a unique linguistic profile. This multi-layered interplay is illustrated by contraction frequencies, which vary from over 1,200 to over 30,000 per million words within the same cohort of models (2026). Ultimately, we conclude that treating LLM output as idiolectal in nature provides a valuable framework with potential implications for research on variation and change, LLM-generated text detection, forensic linguistics and usage-based approaches to language. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-10 in cs.CL). Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.06589 — 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 2026-10-19T09:46:37.205Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-10?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).