#natural language process...
Jun 2026
Detect, Remask, Repair: Diffusion Editing for Faithful Summarization of Evolving Contexts
This work proposes DETECT-REMASK-REPAIR, a diffusion-based framework that identifies, remasks, and repairs outdated regions with masked diffusion language models, and finds that the framework can provide a post-hoc correction step that improves faithfulness for autoregressive systems.
Hao Zou, Zachary Horvitz, C. Karthick et al.
· arXiv.org · 0 citations