Differentially Private In-Context Learning with Nearest Neighbor Search
Koskela, Antti, Kulkarni, Tejas, Zumot, Laith
–arXiv.org Artificial Intelligence
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.
arXiv.org Artificial Intelligence
Nov-7-2025
- Country:
- North America > United States (0.46)
- Genre:
- Research Report (0.82)
- Industry:
- Information Technology > Security & Privacy (0.93)
- Technology: