English(EN) Label-Centric Knowledge Retrieval for Zero-Shot Text Classification

新框架利用 LLM 生成的知识实现高效的零样本文本分类

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-15 04:00

研究人员开发了 SLKR（语义标签知识检索），一个用于零样本文本分类的新型框架，它利用旗舰 LLM 生成标签定义和检索关键词。这个离线知识构建过程作用于标签空间而非整个语料库，分摊了使用强大模型的成本。对于在线推理，一个轻量级 LLM 使用检索到的定义和规则来高效地对文本进行分类，在多个基准测试上取得了优异的成绩，并且输入上下文紧凑，没有特定任务的标记示例。 AI

影响这种方法通过实现高效的零样本分类，可以显著降低大规模数据标记的成本和延迟。

排序理由详细介绍零样本文本分类新方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 16 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 详细介绍零样本文本分类新方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, model release; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.AI TIER_1 English(EN) · Daoping Wu, Dong Wang, Siyu Liu, Chen Liang, Jian Geng, Ziqi Li, Shuguang Xiong, Ying Zhang · 2026-10-15 04:00

面向标签的知识检索用于零样本文本分类

arXiv:2610.16182v1 Announce Type: new Abstract: 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 wi…

本文如何被排名

报道来源 [1]

面向标签的知识检索用于零样本文本分类

相关实体

相关话题