arXiv cs.CL· Umair Mehmood Imam·· 12 小时前AI 评分42
Zuse：面向欧洲语言的多语言决策模型
Zuse: A Decision Model for European Languages
AI 导读
Zuse 是三个决策模型（4B、9B、27B），在冻结的开源基座模型上训练低秩适配器和指针头，覆盖 27 种欧洲语言。在 11 个未参与训练的欧洲数据源、9 类任务、27 种语言的开发集上，27B 模型达到 87.5% 准确率，合并期望校准误差 0.016。
正文 · 原文
Abstract:Decision models read a document and return a probability for each of a fixed set of options instead of generating text. Several appeared in 2026, but none has published results outside English. We describe Zuse, three decision models (4B, 9B and 27B) that train a low-rank adapter and a pointer head on frozen open-weight bases, targeting 27 European languages, and use them to study how this design behaves across languages and tasks. On a broad European suite of 11 sources excluded from training, covering 9 task groups and 27 languages, a development set that also guided model selection, the 27B model reaches 87.5% accuracy with a pooled expected calibration error of 0.016, and 0.035 when weighted per source. Post-hoc analyses of these single-seed results give three findings. First, miscalibration is structured by task rather than language: on parallel reading and topic items in 26 languages the confidence gap varies about as much as sampling noise, while across sources it spans -0.07 to +0.09, with knowledge tasks overconfident and acceptability judgements underconfident at all three sizes, so one fitted temperature cannot correct both. Second, the share of decisions that can be automated at a 5% error budget follows chance-corrected skill (Spearman 0.97 over 33 source and model pairs) more closely than raw accuracy (0.91). Third, reach beyond the training languages is set by the base model: across 210 languages, changing the training run moved scores by at most about 2 points within a size, while languages outside the base's documented list trail by 23 to 28 points at every size. On English public suites Zuse is behind Jev and Kev, including Kev models on the same bases. We also report two pitfalls in building multi-source training data: label-word collision between topic schemes, and an injection augmentation that taught a shortcut. Zuse can be tried at this https URL.
| Comments: | 9 pages, 3 figures, 7 tables |
| Subjects: | Computation and Language (cs.CL); Machine Learning (cs.LG) |
| Cite as: | arXiv:2611.06238 [cs.CL] |
| (or arXiv:2611.06238v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2611.06238 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Umair Mehmood Imam [view email]
[v1]
Wed, 4 Nov 2026 09:45:24 UTC (269 KB)
来源：arXiv cs.CL · arxiv.org