AIBearisharXiv – CS AI · Apr 66/10
🧠
Can VLMs Truly Forget? Benchmarking Training-Free Visual Concept Unlearning
Researchers introduce VLM-UnBench, the first benchmark for evaluating training-free visual concept unlearning in Vision Language Models. The study reveals that realistic prompts fail to genuinely remove sensitive or copyrighted visual concepts, with meaningful suppression only occurring under oracle conditions that explicitly disclose target concepts.