Diversity-aware selection of in-context examples improves performance on complex and out-of-distribution tasks, though effect sizes are often modest.
On the relation between sensitivity and accuracy in in-context learning
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
-
The Role of Diversity in In-Context Learning for Large Language Models
Diversity-aware selection of in-context examples improves performance on complex and out-of-distribution tasks, though effect sizes are often modest.