Pith. sign in

Title resolution pending

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

1 Pith paper citing it

fields

cs.CL 1

years

2025 1

verdicts

CONDITIONAL 1

representative citing papers

Surprise Calibration for Better In-Context Learning

cs.CL · 2025-06-15 · conditional · novelty 6.0

Surprise Calibration uses the model's own surprise at each demonstration's label to dynamically correct class priors in in-context learning, improving accuracy on eight NLP benchmarks.

citing papers explorer

Showing 1 of 1 citing paper.

  • Surprise Calibration for Better In-Context Learning cs.CL · 2025-06-15 · conditional · none · ref 4

    Surprise Calibration uses the model's own surprise at each demonstration's label to dynamically correct class priors in in-context learning, improving accuracy on eight NLP benchmarks.