arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2305.14973cs.CL
收藏

OverPrompt:通过高效上下文学习增强ChatGPT

OverPrompt: Enhancing ChatGPT through Efficient In-Context Learning

Queen Mary University of London(伦敦玛丽女王大学);King’s College London(伦敦国王学院);The Alan Turing Institute(艾伦·图灵研究所)

Jiazheng Li, Runcong Zhao, Yongxin Yang, Yulan He, Lin Gui

AI总结:

针对大语言模型零样本提示的token与时间成本高的问题,提出OverPrompt方法,利用上下文学习处理多任务输入降本,实验验证其能兼顾成本与性能,且适配多模型与不同输入排序。

摘要:

预训练大语言模型的卓越表现已革新了各类自然语言处理应用。由于参数量庞大且运行成本高昂,企业或机构往往采用零样本提示技术将模型迁移至目标任务。然而,token与时间的过高成本阻碍了其在实际应用中的落地。我们提出OverPrompt,利用大语言模型的上下文学习能力处理多个任务输入,从而降低token与时间成本。该方法凭借更优的条件分布映射,有望在API查询过程中提升任务性能。在多类分类数据集上的评估实验表明,OverPrompt可实现具备成本效益的零样本分类,且不会对任务性能造成显著损害,在部分场景下甚至能有所提升。我们在多种大语言模型上开展了消融研究,同时探究了该提示策略对不同输入排序的鲁棒性,为该方法在各类任务中的更广泛适用性提供了宝贵见解。这些发现也表明,我们的方法可通过API与大语言模型实现更顺畅的集成。

英文摘要:

The remarkable performance of pre-trained large language models has revolutionised various natural language processing applications. Due to huge parametersizes and extensive running costs, companies or organisations tend to transfer the models to the target task by zero-shot prompting techniques. However, the prohibitive costs of tokens and time have hindered their adoption in applications. We propose OverPrompt, leveraging the in-context learning capability of LLMs to handle multiple task inputs, thereby reducing token and time costs. This approach could potentially improve task performance during API queries due to better conditional distribution mapping. Evaluated across diverse classification datasets, our experiments show that OverPrompt can achieve cost-efficient zero-shot classification without causing significant detriment to task performance, and in some cases, even improving it. An ablation study conducted on various LLMs, along with an investigation into the robustness of our prompting strategy to different input ordering, offers valuable insights into the broader applicability of our method across diverse tasks. These findings also suggest a more seamless integration of our method with LLMs through an API.

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。

↑