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 2109.07830cs.CLcs.AIcs.LG
收藏

GPTk语言的教学大纲重构

Reframing Instructional Prompts to GPTk's Language

Allen Institute for AI(艾伦人工智能研究所);University of Washington(华盛顿大学);Arizona State University(亚利桑那州立大学)

Swaroop Mishra, Daniel Khashabi, Chitta Baral, Yejin Choi, Hannaneh Hajishirzi

摘要:

对于语言模型(LM),哪种教学提示更容易遵循?我们研究这个问题进行了广泛的实证分析,阐明了成功的教学提示的重要特征。具体来说,我们研究了几类重新组织的技巧,手动重新制定的提示更有效的。一些示例包括将复杂任务指令分解成多个较简单的任务或将指令逐项分解成顺序步骤。我们的实验比较了在6个类别的12个NLP任务上,用重构指令提示LM的zero-shot和Few-Shot性能。与原始指令相比,我们的重构指令在不同大小的LM上都有显着的改进。例如,相同的重构提示在所有任务上平均分别将GPT 3系列和GPT 2系列的Few-Shot性能提高了12.5%和6.7%。此外,重构指令减少了在Few-Shot设置中提示LM所需的示例数量。我们希望这些技巧驱动的技术将为未来更有效的提示算法铺平道路。

英文摘要:

What kinds of instructional prompts are easier to follow for Language Models (LMs)? We study this question by conducting extensive empirical analysis that shed light on important features of successful instructional prompts. Specifically, we study several classes of reframing techniques for manual reformulation of prompts into more effective ones. Some examples include decomposing a complex task instruction into multiple simpler tasks or itemizing instructions into sequential steps. Our experiments compare the zero-shot and few-shot performance of LMs prompted with reframed instructions on 12 NLP tasks across 6 categories. Compared with original instructions, our reframed instructions lead to significant improvements across LMs with different sizes. For example, the same reframed prompts boost few-shot performance of GPT3-series and GPT2-series by 12.5% and 6.7% respectively averaged over all tasks. Furthermore, reframed instructions reduce the number of examples required to prompt LMs in the few-shot setting. We hope these empirically-driven techniques will pave the way towards more effective future prompting algorithms.

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。

↑