标签措辞增强的typed-decision编码器研究：对生僻词有效，对缩写和代码无效
Label-Wording Augmentation in a Typed-Decision Encoder: Gains on Unfamiliar Words, Not on Abbreviations or Codes
AI 导读
一项arXiv研究比较了307M参数多语种交叉编码器Ru-Jev的两个版本，新版在训练中加入以多种表面形式呈现标签的增强方法。在由普通词和外来词（英语衍生行话、办公俚语、部门名称）构成的保留词表上，增强版准确率全面提升，最高提升0.24，其中11项增益通过Holm校正；但对缩写无改善，去除与训练选项相关的标签后，两版在不透明代码上均处于或低于随机水平。
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.AI · arxiv.org