arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~

一种自学分类器:用于动态文档分类的自我改进冻结门训练(SIFT)

A Classifier That Teaches Itself: Self-Improving, Frozen-gate Training (SIFT) for Dynamic Document Classification

Bogdan Raduta, Horia Velicu, Alexandru Preda, Serban Chiricescu

arXiv 2607.18358首次发表:更新:

AI 中文总结

研究针对企业文档分类难题,提出SIFT动态分类器服务,通过低成本管道、特定机制及判断反馈实现自我改进,解决标注和安全问题,介绍其架构、机制及部署示例,探讨边际标注成本趋零的经济性。

AI 中文摘要

文档分类在实验室中已解决,但在企业中仍未解决。阻碍因素并非模型架构,而是模型训练前的标注项目以及企业对模型自我再训练的担忧。我们提出了SIFT(自我改进冻结门训练),一种动态分类器服务,它解决了这两个问题。SIFT通过一个低成本的CPU管道进行分类,使用SPLADE稀疏编码器和LightGBM头,仅将低置信度的少数页面提交给LLM判断。判断结果被写回标注语料库,使昂贵的模型不断教导便宜的模型。引入新文档家族只需声明性捆绑、标签空间、锚定短语和判断词汇表,而非标注项目。更难的问题是安全性,SIFT通过两部分促进门解决,即关键标签F1回归检查和模型从未训练过的冻结黄金回归集,两者均可否决升级。这使得“无需人工每月再训练”从鲁莽变为常规。我们描述了架构、自我馈送语料库循环、冻结门促进机制和一个多域部署示例,并讨论了边际标注成本趋于零的分类器的经济性。

英文摘要

Document classification is a solved problem in the laboratory and an unsolved one in the enterprise. The blocker is rarely model architecture; it is the labeling project that must precede a model and the institutional fear of letting a model retrain itself once one exists. We present SIFT (Self-Improving, Frozen-gate Training), a dynamic classifier service, which attacks both. SIFT serves classification from a deliberately cheap, CPU-bound pipeline, a SPLADE sparse encoder feeding a LightGBM head, and escalates only the low-confidence minority of pages to an LLM judge. The judge's verdicts are written back into a labeled corpus, so the expensive model continuously teaches the cheap one: the escalation rate falls, the corpus grows from production traffic rather than from an up-front annotation effort, and accuracy compounds with use. Onboarding a new document family requires only a declarative bundle, label space, anchor phrases, and a judge glossary, not a labeling project. The harder problem is safety: an autonomously retraining classifier can silently regress. SIFT resolves this with a two-part promote gate, a critical-label F1 regression check plus a frozen golden regression set the model is never trained on, either of which vetoes promotion. This turns "retrain monthly without a human" from reckless into routine. We describe the architecture, the self-feeding corpus loop, the frozen-gate promotion mechanism, and an illustrative multi-domain deployment, and we discuss the economics of a classifier whose marginal labeling cost trends toward zero.

Comments12 pages, 2 figures

论文原文

arXiv 摘要页 · PDF 原文 · HTML 原文

↑