Hybrid demonstration selection that adds 20 similar examples to a large cached random or k-means set matches or beats similarity-only selection at up to 10x lower estimated inference cost in many-shot ICL.
impact of sample selection on in-context learning for entity extraction from scientific writing
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
-
Towards Compute-Optimal Many-Shot In-Context Learning
Hybrid demonstration selection that adds 20 similar examples to a large cached random or k-means set matches or beats similarity-only selection at up to 10x lower estimated inference cost in many-shot ICL.