Learning To Retrieve Prompts for In-Context Learning

Exploring foci of: Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies Learning To Retrieve Prompts for In-Context Learning January 2022 • Ohad Rubin, Jonathan Herzig, Jonathan Berant In-context learning is a recent paradigm in natural language understanding, where a large pre-trained language model (LM) observes a test instance and a few training examples as its input, and directly decodes the output without any update to its parameters. However, performance has been shown to strongly depend on the selected training examples (termed prompts). In this work, we propose an efficient method for retrieving prompts for in-context learning using annotated data and an LM. Given an input-output pair, w… Open Article Page

Computer Science Artificial Intelligence Training, Validation, And Test Data Sets Machine Learning Algorithm Paleontology Biology Open Article