CrossICL reuses demonstrations from similar source tasks, rewriting them into the target task's format, and improves zero-shot ICL on Super-NI without target-task annotations.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
CrossICL: Cross-Task In-Context Learning via Unsupervised Demonstration Transfer
CrossICL reuses demonstrations from similar source tasks, rewriting them into the target task's format, and improves zero-shot ICL on Super-NI without target-task annotations.