DP-TabICL: In-Context Learning with Differentially Private Tabular Data

arXiv:2403.05681v1 Announce Type: new
Abstract: In-context learning (ICL) enables large language models (LLMs) to adapt to new tasks by conditioning on demonstrations of question-answer pairs and it has been shown to have comparable performance to costly model retraining and fine-tuning. Recently, ICL has been extended to allow tabular data to be used as demonstration examples by serializing individual records into natural language formats. However, it has been shown that LLMs can leak information contained in prompts, and since tabular data …

arxiv context cs.ai cs.cr cs.lg data fine-tuning language language models large llms performance private question