Metraipolis › archive › dc_73c35d42fb2b

Does AI-Generated Scientific Text Follow Human Argumentation Patterns? A CARS-Based Comparison of Research Article Introductions — arXiv:2610.01353

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.01353
License (as archived)
CC0-1.0
Archived
2026-10-06T13:55:32.892Z
SHA-256 of the archived text
b4011c2f7f3fd99065ef21c0b52aeceb7b6c08a142bc7bfc0844d7171f785a55
Stable URL of this page
https://metraipolis.com/documento/dc_73c35d42fb2b

How to cite

Does AI-Generated Scientific Text Follow Human Argumentation Patterns? A CARS-Based Comparison of Research Article Introductions — arXiv:2610.01353 — arXiv (en), https://arxiv.org/abs/2610.01353 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_73c35d42fb2b (Metraipolis archive dc_73c35d42fb2b, sha256 b4011c2f7f3fd99065ef21c0b52aeceb7b6c08a142bc7bfc0844d7171f785a55)
BibTeX
@misc{dc73c35d42fb2b,
  title = {Does AI-Generated Scientific Text Follow Human Argumentation Patterns? A CARS-Based Comparison of Research Article Introductions — arXiv:2610.01353},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.01353},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_73c35d42fb2b; sha256 b4011c2f7f3fd99065ef21c0b52aeceb7b6c08a142bc7bfc0844d7171f785a55},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.01353. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large language models are moving from helping write up research to helping do it, which makes it important to know how the scientific text they produce differs from human writing. Work on this question has stayed mostly at the surface, using lexical and stylistic cues that light paraphrasing erases. We look instead at rhetorical structure, the sequence of argumentative moves through which a text makes its case. We study research-article introductions under Swales' CARS model, and compare original introductions from published linguistics articles with generated counterparts of the same papers. We find that human-written introductions are more flexible in which moves they use and in what order, while the generated ones are more uniform. Giving the models the CARS definitions makes them more rigid.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-02 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2610.01353 — 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 2026-10-06T12:15:34.714Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-10-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).