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 https://github.com/bigscience-workshop/promptsource.
PromptSource: An Integrated Development Environment and Repository for Natural Language Prompts
PromptSource provides tools for collaborative prompt development and sharing for training and querying language models.
- Year
- 2022
- Venue
- ACL 2022 5
- Authors
- 27
- Hosting
- Abstract onlyARXIV-DEFAULT
Cite
Notes
Only stored in your browser.
Attribution
- Abstract & full text
- arxiv.org/abs/2202.01279v3ARXIV-DEFAULT
- TL;DR
- Semantic Scholar
Abstract
Authors
27Zheng Xin YongZhiqing SunAlexander M. RushVictor SanhXiangru TangColin RaffelThibault FevryManan DeyGunjan ChhablaniCanwen XuAndrea SantilliStephen H. BachAlbert WebsonNihal V. NayakAbheesht SharmaTaewoon KimM Saiful BariZaid AlyafeaiSrulik Ben-DavidHan WangJason Alan FriesMaged S. Al-shaibaniShanya SharmaUrmish ThakkerKhalid AlmubarakDragomir RadevMike Tian-Jian Jiang