AI RESEARCH
Erasure or Erosion? Evaluating Compositional Degradation in Unlearned Text-To-Image Diffusion Models
arXiv CS.CV
•
ArXi:2604.04575v1 Announce Type: new Post-hoc unlearning has emerged as a practical mechanism for removing undesirable concepts from large text-to-image diffusion models. However, prior work primarily evaluates unlearning through erasure success; its impact on broader generative capabilities remains poorly understood. In this work, we conduct a systematic empirical study of concept unlearning through the lens of compositional text-to-image generation.