Metraipolis › archive › dc_ee288dd2e808

Sentence Specificity Scores for Collaborative Technical Documentation: A Domain-Transfer Study — arXiv:2610.01046

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.01046
License (as archived): CC0-1.0
Archived: 2026-10-06T13:54:45.743Z
SHA-256 of the archived text: 35285853716118d3f558cf7b46fb824c11c8470ac6fdd477675fd57282b28a4f
Stable URL of this page: https://metraipolis.com/documento/dc_ee288dd2e808

How to cite

Sentence Specificity Scores for Collaborative Technical Documentation: A Domain-Transfer Study — arXiv:2610.01046 — arXiv (en), https://arxiv.org/abs/2610.01046 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ee288dd2e808 (Metraipolis archive dc_ee288dd2e808, sha256 35285853716118d3f558cf7b46fb824c11c8470ac6fdd477675fd57282b28a4f)

BibTeX

@misc{dcee288dd2e808,
  title = {Sentence Specificity Scores for Collaborative Technical Documentation: A Domain-Transfer Study — arXiv:2610.01046},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.01046},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ee288dd2e808; sha256 35285853716118d3f558cf7b46fb824c11c8470ac6fdd477675fd57282b28a4f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.01046. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Collaboration depends on shared context, and technical documentation is one way that context persists across people and AI teammates. Specificity, the amount and exactness of detail expressed in language, shapes what information documentation captures and how precisely that information is communicated. This work audits sentence-specificity scoring artifacts on technical documentation and tests whether scores applied only after generation help choose among fixed LLM-generated revisions. Across Wikipedia and three technical-documentation corpora, the fixed general-domain predictor SpeciTeller and the pinned post-publication author-repository implementation of Ko et al.'s target-adapted predictor produce different corpus orders and same-sentence rank agreement from -0.066 to 0.510. Strict filtering and token-length adjustment change these patterns without reconciling them. In the Gemma set, SpeciTeller ranking raises direction-valid selection from 71.7% to 83.3% (+11.7 points; 95% source-case bootstrap interval +1.7 to +21.7); in the GPT-OSS-120B set, SpeciTeller ranking raises direction-valid selection from 51.7% to 56.7% (+5.0 points; 95% source-case bootstrap interval -6.7 to +16.7), and every primary single-score GPT-OSS-120B interval includes zero. These findings tie score interpretation and decision value to the predictor and candidate set.

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) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.01046 — 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 2026-10-06T12:15:34.671Z 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).