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~~
arXiv 2610.16182cs.AI
收藏

面向零样本文本分类的以标签为中心的知识检索

Label-Centric Knowledge Retrieval for Zero-Shot Text Classification

Zhejiang Lab(之江实验室)

Daoping Wu, Dong Wang, Siyu Liu, Chen Liang, Jian Geng, Ziqi Li, Shuguang Xiong, Ying Zhang

AI总结:

本文提出以标签为中心的SLKR框架,将离线构建标签知识库与轻量级在线推理分离,在四个数据集上用小型LLM实现零样本文本分类的最优或接近最优性能,且推理高效。

摘要:

旗舰级大语言模型(LLM)具备丰富的通用知识与强大的推理能力,但其高昂的推理成本与延迟限制了其在大规模数据标注场景中的应用。本文研究无需任务特定标注样本或分类器反馈、基于语义有意义的标签与任务描述的零样本文本分类任务。我们提出了SLKR(Semantic Label Knowledge Retrieval,语义标签知识检索),这是一种以标签为中心的检索增强生成框架,它将离线知识构建与轻量级在线推理分离开来。在离线阶段,旗舰级LLM会为潜在易混淆的标签对独立生成标签定义、检索关键词以及边界规则,形成可复用的标签知识库。由于该构建过程是在标签空间而非输入语料库上进行的,其一次性的旗舰级成本可在大规模推理中被分摊。在在线阶段,混合语义与词汇检索首先识别出前K个候选标签,随后选择最多M个与输入相关的、连接候选标签对的边界规则。轻量级LLM通过一次调用,利用检索到的定义与规则完成最终分类。在三个公开基准数据集与一个真实世界多语种书籍分类数据集上,SLKR在使用Qwen3.5-4B模型时取得了四个数据集上的最佳结果,在使用Ministral-3-3B模型时取得了四个数据集中三个的最佳结果,同时使用了紧凑的输入上下文且未使用任务特定标注样本。边界消融实验进一步表明,检索少量与输入相关的规则可在大幅减少上下文使用的情况下,保持与使用所有边界规则相近的性能,支持将旗舰级生成的标签知识高效复用至轻量级分类任务中。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑