arXiv：cs.LG（机器学习，全量分类）· Rocker D'Antonio, Thomas Benton Townsend, Dimitrios Michael Manias·· 9 小时前AI 评分29
面向协作技术文档的句子特异性评分：一项领域迁移研究
Sentence Specificity Scores for Collaborative Technical Documentation: A Domain-Transfer Study
AI 导读
研究审计了技术文档上的句子特异性评分工具，发现通用域预测器 SpeciTeller 与 Ko 等人目标适配预测器在 Wikipedia 及三个技术文档语料上给出不同的语料排序，同句排名一致性从 -0.066 到 0.510。
正文
Abstract: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.
| Comments: | 17 pages, 2 figures. Accepted for publication in the 2026 IEEE 12th International Conference on Collaboration and Internet Computing (CIC) |
| Subjects: | Computation and Language (cs.CL); Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.01046 [cs.CL] |
| (or arXiv:2610.01046v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.01046 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Rocker DAntonio [view email]
[v1]
Thu, 1 Oct 2026 04:38:39 UTC (96 KB)
来源：arXiv：cs.LG（机器学习，全量分类） · arxiv.org