Plausible Token Amplification for Improving Accuracy of Differentially Private In-Context Learning Based on Implicit Bayesian Inference
Abstract
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, its theoretical basis remains unexplored. By interpreting ICL as implicit Bayesian inference on a concept underlying demonstrations, we not only provide theoretical evidence supporting Tang et al.’s empirical method but also introduce PTA, a refined method for modifying next-token probability distribution. Through the modification, PTA highlights tokens that distinctly represent the ground-truth concept underlying the original demonstrations. As a result, generated DP synthetic demonstrations guide the Large Language Model to successfully infer the ground-truth concept, which improves the accuracy of DP-ICL. Experimental evaluations on both synthetic and real-world text-classification datasets validated the effectiveness of PTA.
Cite
Text
Yamasaki et al. "Plausible Token Amplification for Improving Accuracy of Differentially Private In-Context Learning Based on Implicit Bayesian Inference." Proceedings of the 42nd International Conference on Machine Learning, 2025.Markdown
[Yamasaki et al. "Plausible Token Amplification for Improving Accuracy of Differentially Private In-Context Learning Based on Implicit Bayesian Inference." Proceedings of the 42nd International Conference on Machine Learning, 2025.](https://mlanthology.org/icml/2025/yamasaki2025icml-plausible/)BibTeX
@inproceedings{yamasaki2025icml-plausible,
title = {{Plausible Token Amplification for Improving Accuracy of Differentially Private In-Context Learning Based on Implicit Bayesian Inference}},
author = {Yamasaki, Yusuke and Niwa, Kenta and Chijiwa, Daiki and Fukami, Takumi and Miura, Takayuki},
booktitle = {Proceedings of the 42nd International Conference on Machine Learning},
year = {2025},
pages = {70205-70248},
volume = {267},
url = {https://mlanthology.org/icml/2025/yamasaki2025icml-plausible/}
}