SOURCE-LINKED INTELLIGENCE

Quantization-Robust Unlearning through the Lens of Retain-Forget Loss Landscapes Interaction

arXiv · AI, language, vision and robotics · article · Sep 23, 2026 · UTC

Unlearning ensures LLM compliance by removing the influence of private or copyrighted training data. However, since LLM models typically undergo post-training compression, like quantization, in practical deployment, it has been observed that the unlearning effect can be substantially weakened, with the forgetting behavior degrading more severely than that of model utility. This paper proposes a quantization-robust unlearning framework that makes forgetting robust to quantization while maintaining overall model utility. We analyze this gap through the lens of loss landscape. Specifically, our a

Read original source ↗ Open in workspace

recordType

paper

region

Global