Differentially Private In-Context Learning with Nearest Neighbor Search

📝 Original Info

• Title: Differentially Private In-Context Learning with Nearest Neighbor Search
• ArXiv ID: 2511.04332
• Date: 2025-11-06
• Authors: ** 제공되지 않음 (논문에 명시된 저자 정보가 없습니다) **

📝 Abstract

Differentially private in-context learning (DP-ICL) has recently become an active research topic due to the inherent privacy risks of in-context learning. However, existing approaches overlook a critical component of modern large language model (LLM) pipelines: the similarity search used to retrieve relevant context data. In this work, we introduce a DP framework for in-context learning that integrates nearest neighbor search of relevant examples in a privacy-aware manner. Our method outperforms existing baselines by a substantial margin across all evaluated benchmarks, achieving more favorable privacy-utility trade-offs. To achieve this, we employ nearest neighbor retrieval from a database of context data, combined with a privacy filter that tracks the cumulative privacy cost of selected samples to ensure adherence to a central differential privacy budget. Experimental results on text classification and document question answering show a clear advantage of the proposed method over existing baselines.

💡 Deep Analysis

📄 Full Content

Reference