PromptSource: An Integrated Development Environment and Repository for Natural Language Prompts
This addresses the need for collaborative tools in the emerging area of prompt-based NLP, providing a practical solution for researchers and practitioners, though it is incremental as it builds on existing prompt methods.
The paper tackles the problem of creating, sharing, and using natural language prompts for training and querying language models in NLP by introducing PromptSource, a system that includes a templating language, an iterative development interface, and community guidelines, resulting in over 2,000 prompts for roughly 170 datasets already available.
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.