arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.07386cs.CL
收藏

Chain-of-Layer:通过迭代提示大型语言模型从有限样本中进行分类体系归纳

Chain-of-Layer: Iteratively Prompting Large Language Models for Taxonomy Induction from Limited Examples

University of Notre Dame(圣母大学);University of Washington(华盛顿大学)

Qingkai Zeng, Yuyang Bai, Zhaoxuan Tan, Shangbin Feng, Zhenwen Liang, Zhihan Zhang, Meng Jiang

AI总结:

提出 Chain-of-Layer 框架,通过迭代提示大型语言模型自顶向下逐层选择实体并引入基于集成的排序过滤器减少幻觉,在四个基准上实现了最先进的分类体系归纳性能。

摘要:

自动分类体系归纳对网络搜索、推荐系统和问答至关重要。人工构建分类体系耗费大量人力,使得自动构建极具吸引力。本工作提出 Chain-of-Layer,这是一个上下文学习框架,旨在从给定实体集合中归纳分类体系。Chain-of-Layer 将任务分解为在每一层选择相关候选实体,并自顶向下逐步构建分类体系。为减少错误,我们引入基于集成的排序过滤器,以减少每次迭代中产生的幻觉内容。通过大量实验,我们证明 Chain-of-Layer 在四个真实世界基准上达到了最先进的性能。

英文摘要:

Automatic taxonomy induction is crucial for web search, recommendation systems, and question answering. Manual curation of taxonomies is expensive in terms of human effort, making automatic taxonomy construction highly desirable. In this work, we introduce Chain-of-Layer which is an in-context learning framework designed to induct taxonomies from a given set of entities. Chain-of-Layer breaks down the task into selecting relevant candidate entities in each layer and gradually building the taxonomy from top to bottom. To minimize errors, we introduce the Ensemble-based Ranking Filter to reduce the hallucinated content generated at each iteration. Through extensive experiments, we demonstrate that Chain-of-Layer achieves state-of-the-art performance on four real-world benchmarks.

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。

↑