pith. sign in

Z-ICL: Zero-shot in-context learning with pseudo-demonstrations

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.CL 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

Self-Improving In-Context Learning

cs.CL · 2026-05-22 · unverdicted · novelty 7.0

A test-time zeroth-order optimization of prompt embeddings using a bounded self-supervised proxy from demonstration log-probabilities improves ICL accuracy and correlates with gains across tasks.

citing papers explorer

Showing 1 of 1 citing paper.

  • Self-Improving In-Context Learning cs.CL · 2026-05-22 · unverdicted · none · ref 29

    A test-time zeroth-order optimization of prompt embeddings using a bounded self-supervised proxy from demonstration log-probabilities improves ICL accuracy and correlates with gains across tasks.