SLKR：旗舰模型离线建标签知识，小模型单次调用完成分类
Label-Centric Knowledge Retrieval for Zero-Shot Text Classification
给文本批量打标签太贵？SLKR 让旗舰模型离线写好标签规则，Qwen3.5-4B 一次调用就能分类。
一篇 arXiv 论文提出 SLKR 框架，把零样本文本分类拆成离线知识构建与在线轻量推理两段，全程不需要任务标注样本。离线阶段由旗舰 LLM 一次性生成标签定义、检索关键词，以及针对易混淆标签对的边界规则，形成可复用的标签知识库。在线阶段先用语义加词法混合检索筛出 top-K 候选标签，再取最多 M 条与输入相关的边界规则，轻量模型单次调用即可完成分类。在 3 个公开基准和 1 个多语言图书分类数据集上，Qwen3.5-4B 在全部 4 个数据集取得最优结果，Ministral-3-3B 在其中 3 个上最优。消融实验显示，只检索少量与输入相关的边界规则就能接近使用全部规则的效果，上下文长度明显更短。
Label-Centric Knowledge Retrieval for Zero-Shot Text Classification
Flagship large language models (LLMs) offer rich general knowledge and strong reasoning capabilities, but their high inference cost and latency limit their use for large-scale data labeling. We study zero-shot text classification with semantically meaningful labels and task descriptions, without task-specific labeled examples or classifier feedback. We propose \textbf{SLKR} (Semantic Label Knowledge Retrieval), a label-centric retrieval-augmented generation framework that separates offline knowledge construction from lightweight online inference. Offline, a flagship LLM independently generates label definitions, retrieval keywords, and boundary rules for potentially confusable label pairs, forming a reusable label-knowledge store. Because this construction operates over the label space rather than the input corpus, its one-time flagship cost can be amortized across large-scale inference. Online, hybrid semantic and lexical retrieval first identifies the top-$K$ candidate labels and then selects up to $M$ input-relevant boundary rules connecting candidate-label pairs. A lightweight LLM performs the final classification in a single call using the retrieved definitions and rules. Across three public benchmarks and a real-world multilingual book-classification dataset, SLKR achieves the best results on all four datasets with Qwen3.5-4B and on three of four with Ministral-3-3B, while using compact input contexts and no task-specific labeled examples. Boundary ablations further show that retrieving a small set of input-relevant rules preserves performance close to using all boundaries with substantially less context, supporting efficient reuse of flagship-generated label knowledge for lightweight classification.
