arXiv：cs.LG（机器学习，全量分类）· Jiamu Zhang, Tianze Yang, Yucheng Shi, Evan Chen, Zixiang Nie, Kelly Wan, Liangjie Hong, Ninghao Liu, Liang Wu·· 14 小时前AI 评分41
AnyJev 技术报告：无需梯度更新，从预训练 LLM 单次 prefill 中读取类型化决策
AnyJev Technical Report
AI 导读
AnyJev 能从预训练指令微调语言模型的一次 prefill 中读取类型化决策，通过除以无标注输入估计的标签先验、并对选项列表的 K 次循环轮换取对数概率平均，在无梯度更新、无参数改动的情况下修正标签与位置偏差。
正文
Abstract:A typed decision is a choice among a fixed set of options, returned as a probability rather than as text. Systems that need typed decisions today use models trained for that purpose. This report describes AnyJev, which reads a typed decision from one prefill of a pretrained instruction-tuned language model. The readout restricts the next-token distribution at the answer position to the option tokens. It has two defects: the model assigns higher probability to some labels whatever the input, and to some positions in the option list. AnyJev corrects both with no gradient steps and no parameter changes: it divides out a label prior estimated from unlabelled inputs, and it averages log-probabilities over the K cyclic rotations of the option list. On two 20-option tasks the rotations lower the order-flip rate from 0.33 to 0.14 and from 0.33 to 0.18, and raise accuracy on 11 of 11 models on both. Reading every rotation requires K prefills. A stopping rule selected against the full-rotation decision on unlabelled states cuts that. Selecting the threshold on one unlabelled split and bounding its disagreement on a second, it reads 10.6 rotations of 18 at a verified 0.008 bound on two of four cells; selected and bounded on one split, as our serving run did, it reads 7.3 and serves 2.2 times as many decisions per second on vLLM. The code is open source.
| Comments: | 22 pages, 5 figures. Early report on work in development. Code: this https URL |
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.00831 [cs.LG] |
| (or arXiv:2610.00831v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.00831 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Jiamu Zhang [view email]
[v1]
Wed, 30 Sep 2026 23:43:04 UTC (314 KB)
来源：arXiv：cs.LG（机器学习，全量分类） · arxiv.org