Reframing Instructional Prompts to GPTk's Language

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

Research output: Chapter in Book/Report/Conference proceedingConference contribution

35 Scopus citations


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.

Original languageEnglish (US)
Title of host publicationACL 2022 - 60th Annual Meeting of the Association for Computational Linguistics, Findings of ACL 2022
EditorsSmaranda Muresan, Preslav Nakov, Aline Villavicencio
PublisherAssociation for Computational Linguistics (ACL)
Number of pages24
ISBN (Electronic)9781955917254
StatePublished - 2022
Event60th Annual Meeting of the Association for Computational Linguistics, ACL 2022 - Dublin, Ireland
Duration: May 22 2022May 27 2022

Publication series

NameProceedings of the Annual Meeting of the Association for Computational Linguistics
ISSN (Print)0736-587X


Conference60th Annual Meeting of the Association for Computational Linguistics, ACL 2022

ASJC Scopus subject areas

  • Computer Science Applications
  • Linguistics and Language
  • Language and Linguistics


Dive into the research topics of 'Reframing Instructional Prompts to GPTk's Language'. Together they form a unique fingerprint.

Cite this