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.
CoRR , volume =
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CL 2representative citing papers
PEML co-optimizes continuous prompts and low-rank adaptations to deliver up to 6.67% average accuracy gains over existing multi-task PEFT methods on GLUE, SuperGLUE, and other benchmarks.
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.
-
PEML: Parameter-efficient Multi-Task Learning with Optimized Continuous Prompts
PEML co-optimizes continuous prompts and low-rank adaptations to deliver up to 6.67% average accuracy gains over existing multi-task PEFT methods on GLUE, SuperGLUE, and other benchmarks.