SOURCE-LINKED INTELLIGENCE

The Privacy-Hallucination Tradeoff in Differentially Private Language Models

arXiv · AI, language, vision and robotics · article · Aug 31, 2026 · UTC

Both privacy and factual accuracy are paramount in high-stakes domains like healthcare. Concerningly, we uncover and investigate a privacy-hallucination tradeoff in differentially private (DP) language models. First, we empirically show that models pre-trained or fine-tuned with DP tend to produce more hallucinations than non-DP counterparts, with increased severity as the privacy budget grows stricter. Second, we investigate model properties driving this tradeoff, demonstrating that DP mechanisms flatten output distributions, potentially redistributing probability mass toward factually incorr

Read original source ↗ Open in workspace

recordType

paper

region

Global