The unreasonable effectiveness of large language models for low-resource clause-level morphology: In-context generalization or prior exposure?

AbstractThis paper describes the submission of Team “Giving it a Shot” to the AmericasNLP 2024 Shared Task on Creation of Educational Materials for Indigenous Languages. We use a simple few-shot prompting approach with several state of the art large language models, achieving competitive performance on the shared task, with our best system placing third overall. We perform a preliminary analysis to determine to what degree the performance of our model is due to prior exposure to the task languages, finding that generally our performance is better explained as being derived from in-context learning capabilities.