arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2401.07059cs.CY
收藏

使用大型语言模型对去中心化自治组织提案进行分类

Classifying Proposals of Decentralized Autonomous Organizations Using Large Language Models

Christian Ziegler, Marcos Miranda, Guangye Cao, Gustav Arentoft, Doo Wan Nam

AI总结:

针对DAO提案分类依赖人工、成本高的问题,本文提出通过LLM迭代细化类别与提示词的方法,在100份提案上实现95%准确率,验证了LLM自动化文本语境数据标注的潜力。

摘要:

我们的研究展示了大型语言模型(LLM)在自动化复杂数据集分类方面的有效应用。我们特别针对去中心化自治组织(DAO)的提案,因为这类数据的分类需要理解语境,因而依赖人类专业知识,导致该任务成本高昂。本研究采用迭代方法来确定类别,并在每次迭代中进一步细化类别和提示词,最终在对100份提案组成的集合进行分类时达到了95%的准确率。借此,我们证明了LLM在有效自动化依赖文本语境的数据标注任务方面的潜力。

英文摘要:

Our study demonstrates the effective use of Large Language Models (LLMs) for automating the classification of complex datasets. We specifically target proposals of Decentralized Autonomous Organizations (DAOs), as the clas-sification of this data requires the understanding of context and, therefore, depends on human expertise, leading to high costs associated with the task. The study applies an iterative approach to specify categories and further re-fine them and the prompt in each iteration, which led to an accuracy rate of 95% in classifying a set of 100 proposals. With this, we demonstrate the po-tential of LLMs to automate data labeling tasks that depend on textual con-text effectively.

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。

↑