Randomly replacing labels in in-context demonstrations barely hurts performance, showing that label space, input distribution, and sequence format drive in-context learning more than ground-truth labels.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
representative citing papers
Multitask fine-tuning of an encoder-decoder model on prompted datasets produces zero-shot generalization that often beats models up to 16 times larger on standard benchmarks.
Atlas reaches over 42% accuracy on Natural Questions with only 64 examples, outperforming a 540B-parameter model by 3% with 50x fewer parameters.
citing papers explorer
-
Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?
Randomly replacing labels in in-context demonstrations barely hurts performance, showing that label space, input distribution, and sequence format drive in-context learning more than ground-truth labels.
-
Multitask Prompted Training Enables Zero-Shot Task Generalization
Multitask fine-tuning of an encoder-decoder model on prompted datasets produces zero-shot generalization that often beats models up to 16 times larger on standard benchmarks.
-
Atlas: Few-shot Learning with Retrieval Augmented Language Models
Atlas reaches over 42% accuracy on Natural Questions with only 64 examples, outperforming a 540B-parameter model by 3% with 50x fewer parameters.