Stephen H. BachVictor SanhZheng-Xin YongAlbert WebsonColin RaffelNihal V. NayakAbheesht SharmaTaewoon KimM Saiful BariThibault FevryZaid AlyafeaiManan DeyAndrea SantilliZhiqing SunSrulik Ben-DavidCanwen XuGunjan ChhablaniHan WangJason Alan FriesMaged S. Al-shaibaniShanya SharmaUrmish ThakkerKhalid AlmubarakXiangru TangDragomir RadevMike Tian-Jian JiangAlexander M. Rush


Working Group: Modeling: Prompt Engineering


PromptSource is a system for creating, sharing, and using natural language prompts. Prompts are functions that map an example from a dataset to a natural language input and target output. Using prompts to train and query language models is an emerging area in NLP that requires new tools that let users develop and refine these prompts collaboratively. PromptSource addresses the emergent challenges in this new setting with (1) a templating language for defining data-linked prompts, (2) an interface that lets users quickly iterate on prompt development by observing outputs of their prompts on many examples, and (3) a community-driven set of guidelines for contributing new prompts to a common pool. Over 2,000 prompts for roughly 170 datasets are already available in PromptSource. PromptSource is available at this https URL.

PromptSource 1.jpeg