arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.08493cs.LG
收藏

一个Prompt值多少个数据点?

How Many Data Points is a Prompt Worth?

Hugging Face

Teven Le Scao, Alexander M. Rush

摘要:

当微调预训练模型进行分类时,研究人员要么使用通用模型头,要么使用特定于任务的提示进行预测。提示的支持者认为,提示提供了一种注入特定任务指导的方法,这在低数据制度中是有益的。我们的目标是通过在公平的环境中对提示进行严格的测试来量化这种好处:在许多任务和数据大小的相同条件下比较提示和基于头部的微调。通过控制许多优势来源,我们发现激励确实提供了一个好处,而且这个好处可以量化每个任务。结果表明,提示通常值得在分类任务中平均使用100个数据点。

英文摘要:

When fine-tuning pretrained models for classification, researchers either use a generic model head or a task-specific prompt for prediction. Proponents of prompting have argued that prompts provide a method for injecting task-specific guidance, which is beneficial in low-data regimes. We aim to quantify this benefit through rigorous testing of prompts in a fair setting: comparing prompted and head-based fine-tuning in equal conditions across many tasks and data sizes. By controlling for many sources of advantage, we find that prompting does indeed provide a benefit, and that this benefit can be quantified per task. Results show that prompting is often worth 100s of data points on average across classification tasks.

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。

↑