arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2403.08430cs.SEcs.AI
收藏

基于搜索的LLM学习样本优化用于故事点估算

Search-based Optimisation of LLM Learning Shots for Story Point Estimation

J.P.Morgan AI Research(摩根大通人工智能研究院)

Vali Tawosi, Salwa Alamir, Xiaomo Liu

AI总结:

本文利用基于搜索的软件工程方法优化LLM少样本学习的示例数量与组合,以提升敏捷故事点估算性能,在三个数据集上平均误差降低59.34%。

摘要:

大型语言模型(LLM)用于执行机器学习任务的方式之一是,在要求其产生预测之前,先向其提供几个示例。这是一种称为少样本学习的元学习过程。在本文中,我们利用现有的基于搜索的方法来优化示例的数量和组合,以提高LLM在估算新的敏捷任务故事点时的估算性能。我们的初步结果表明,我们的SBSE技术相对于零样本设置,在三个数据集上将LLM的估算性能平均提高了59.34%(以估算的平均绝对误差衡量)。

英文摘要:

One of the ways Large Language Models (LLMs) are used to perform machine learning tasks is to provide them with a few examples before asking them to produce a prediction. This is a meta-learning process known as few-shot learning. In this paper, we use available Search-Based methods to optimise the number and combination of examples that can improve an LLM's estimation performance, when it is used to estimate story points for new agile tasks. Our preliminary results show that our SBSE technique improves the estimation performance of the LLM by 59.34% on average (in terms of mean absolute error of the estimation) over three datasets against a zero-shot setting.

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。

↑