Takayuki Miura

Plausible Token Amplification for Improving Accuracy of Differentially Private In-Context Learning Based on Implicit Bayesian Inference

We propose Plausible Token Amplification (PTA) to improve the accuracy of Differentially Private In-Context Learning (DP-ICL) using DP synthetic demonstrations. While Tang et al. empirically improved the accuracy of DP-ICL by limiting vocabulary space during DP synthetic demonstration generation, it…