2 papers
cs.AI2026
JUMP: Efficient Membership Inference on Fine-Tuned Diffusion Language Models
Yeachan Jun, Albert No
Membership inference attacks (MIAs) test whether a candidate example was used to train a language model. Existing attacks on fine-tuned discrete diffusion language models (dLLMs) o…
cs.CL2026
Position: The Term "Machine Unlearning" Is Overused in LLMs
Sangyeon Yoon, Yeachan Jun, Albert No
Large language models increasingly face demands to "forget" training data, knowledge, or behaviors due to regulatory deletion obligations, copyright/licensing disputes, and safety…