Large pre-trained language models have shown promise for few-shot learning, completing text-based tasks given only a few task-specific examples. Will models soon solve classification tasks that have so far been reserved for human research assistants?
RAFT is a few-shot classification benchmark that tests language models:
- across multiple domains (lit reviews, medical data, tweets, customer interaction, etc.)
- on economically valuable classification tasks (someone inherently cares about the task)
- with evaluation that mirrors deployment (50 labeled examples per task, info retrieval allowed, hidden test set)
- Paper (NeurIPS 2021)
We’re considering a successor, RAFT 2. You can participate as co-author by submitting a dataset.