arXiv Computation and Language
Knowledge Editing for Masked Diffusion Language Models
Read the original on arXiv Computation and Language →The paper investigates whether the locate‑then‑edit approach for knowledge editing, previously applied only to autoregressive language models, can be transferred to masked diffusion models (MDMs). It finds that the optimal edit location—an early‑to‑mid‑layer MLP at the last subject token—remains the same for both model types, but that MDMs suffer a sharper decline in performance when editing longer, multi‑token facts. By incorporating intermediate partially‑unmasked states into the edit optimization, the authors restore multi‑token editing performance in MDMs.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.