← Search

Vincent Hanke

2 accepted papers

2026

Benchmarking Empirical Privacy Protection for Adaptations of Large Language Models

ICLR 2026oral

Recent work has applied differential privacy (DP) to adapt large language models (LLMs) for sensitive applications, offering theoretical guarantees. However, its practical effectiveness remains unclear, partly due to LLM pretraining, where overlaps and interdependencies with adaptation data can unde…

Cited by 0SourceScholar
2024

Open LLMs are Necessary for Current Private Adaptations and Outperform their Closed Alternatives

NeurIPS 2024poster

While open Large Language Models (LLMs) have made significant progress, they still fall short of matching the performance of their closed, proprietary counterparts, making the latter attractive even for the use on highly *private* data. Recently, various new methods have been proposed to adapt clos…

Cited by 2SourcePDFScholar