arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2307.00524cs.CL
收藏

大型语言模型实现少样本聚类

Large Language Models Enable Few-Shot Clustering

Carnegie Mellon University(卡内基梅隆大学);NEC Laboratories Europe(NEC欧洲实验室);Inspired Cognition(灵感认知公司)

Vijay Viswanathan, Kiril Gashteovski, Carolin Lawrence, Tongshuang Wu, Graham Neubig

AI总结:

探讨大型语言模型能否放大专家指导以实现少样本半监督文本聚类,发现将LLM融入聚类前和聚类中阶段能显著提升聚类质量,并允许用户在成本与准确性间权衡。

摘要:

与传统的无监督聚类不同,半监督聚类允许用户提供有意义的数据结构,这有助于聚类算法匹配用户的意图。现有的半监督聚类方法需要专家提供大量反馈才能改进聚类。在本文中,我们探讨大型语言模型(LLM)能否放大专家的指导,从而实现查询高效、少样本的半监督文本聚类。我们展示了LLM在改进聚类方面惊人地有效。我们探索了将LLM融入聚类的三个阶段:聚类前(改进输入特征)、聚类中(向聚类器提供约束)和聚类后(使用LLM进行后校正)。我们发现,在前两个阶段融入LLM通常能显著提升聚类质量,并且LLM允许用户在成本与准确性之间进行权衡以生成理想的聚类。我们发布了代码和LLM提示供公众使用。

英文摘要:

Unlike traditional unsupervised clustering, semi-supervised clustering allows users to provide meaningful structure to the data, which helps the clustering algorithm to match the user's intent. Existing approaches to semi-supervised clustering require a significant amount of feedback from an expert to improve the clusters. In this paper, we ask whether a large language model can amplify an expert's guidance to enable query-efficient, few-shot semi-supervised text clustering. We show that LLMs are surprisingly effective at improving clustering. We explore three stages where LLMs can be incorporated into clustering: before clustering (improving input features), during clustering (by providing constraints to the clusterer), and after clustering (using LLMs post-correction). We find incorporating LLMs in the first two stages can routinely provide significant improvements in cluster quality, and that LLMs enable a user to make trade-offs between cost and accuracy to produce desired clusters. We release our code and LLM prompts for the public to use.

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。

↑