arXiv cs.CL· Vladimir Beskorovainyi·· 12 小时前AI 评分29
Ru-Jev 研究：标签措辞增强提升生词准确率，但对缩写与代码无效
Label-Wording Augmentation in a Typed-Decision Encoder: Gains on Unfamiliar Words, Not on Abbreviations or Codes
AI 导读
307M 参数多语言 cross-encoder Ru-Jev 的后续版本加入标签多表面形式增强，在 18 个路由标签、10 套标签词表上，对普通词与借词（英文衍生术语、办公室俚语、部门名）的准确率在全部设置下均有提升，最高 +0.24，14 项增益中 11 项通过 Holm 校正。
正文 · 原文
Abstract:Typed-decision models score options that the caller supplies at request time, so their accuracy depends on label wording that the model's developer does not control. We compare two releases of a 307M-parameter multilingual cross-encoder, Ru-Jev, trained on thirteen Russian-language tasks; the later release adds an augmentation that presents labels in several surface forms. Holding questions fixed and varying only how eighteen routing labels are worded, we evaluate ten label vocabularies, produced by three separate processes and checked for overlap with the training data, with five candidates per question and, for eight of them, also with eighteen. On held-out vocabularies made of ordinary or borrowed words (English-derived jargon, office slang, department names), the augmented release is more accurate in every setting, by up to 0.24. Eleven of these fourteen gains survive a Holm correction (slang with eighteen candidates and descriptive sentences with five do not), and for jargon on all labels the label-level interval excludes zero in both settings. On abbreviations and opaque codes it gives no usable gain: on abbreviations it is not better, and worse on the clean slice, and on opaque codes both releases stay at or below chance once labels related to training options are removed. In most cells where accuracy rises, the risk-coverage area falls, but with eighteen candidates confident errors rise on jargon and slang. On two datasets neither release saw, accuracy moves by -8.4 and +5.6 points. We also report four evaluation hazards from comparing the two releases.
| Comments: | 11 pages, 6 tables. Model: this https URL ; code: this https URL ; archived release: this https URL |
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Machine Learning (cs.LG) |
| Cite as: | arXiv:2611.08439 [cs.CL] |
| (or arXiv:2611.08439v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2611.08439 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Vladimir Beskorovainyi [view email]
[v1]
Thu, 5 Nov 2026 18:31:24 UTC (15 KB)
来源：arXiv cs.CL · arxiv.org