MDU minimizes forward KL divergence from prompt-conditional to prompt-masked unconditional predictions at masked positions to unlearn knowledge in MDLMs while trading off privacy and utility via temperature scaling.
Rwku: Benchmarking real-world knowledge unlearning for large language models.Advances in Neural Information Processing Systems, 37:98213–98263
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
method 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
method 1polarities
use method 1representative citing papers
PPU-Bench is a real-world benchmark exposing forget-retain trade-offs in MLLM unlearning and motivating Boundary-Aware Optimization to enforce intra-subject factual boundaries.
citing papers explorer
-
PPU-Bench:Real World Benchmark for Personalized Partial Unlearning in Vision Language Models
PPU-Bench is a real-world benchmark exposing forget-retain trade-offs in MLLM unlearning and motivating Boundary-Aware Optimization to enforce intra-subject factual boundaries.