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

Yusuke Yamasaki; Kenta Niwa; Daiki Chijiwa; Takumi Fukami; Takayuki Miura

2025 ICML ICML 2025

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

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

🌉 Interdisciplinary Bridge - Artificial Intelligence and Natural Language Processing

Authors

Yusuke Yamasaki, Kenta Niwa, Daiki Chijiwa, Takumi Fukami, Takayuki Miura

Topics

Machine Learning > Optimization & Theory > Bayesian Inference Natural Language Processing > Applications > Text Classification Artificial Intelligence > Core AI > Large Language Models

Keywords

next-token probability distribution differentially private in-context learning dp synthetic demonstrations ground-truth concept implicit bayesian inference plausible token amplification

Download PDF