AINeutralarXiv – CS AI · 15h ago6/10
🧠
Targeted Remasking: Replacing Token Editing with Token-to-Mask Refinement in Discrete Diffusion Language Models
Researchers propose Token-to-Mask (T2M) remasking as an improved alternative to Token-to-Token editing in discrete diffusion language models, addressing fundamental limitations in error detection and context corruption. The method resets suspected erroneous tokens to mask state for re-prediction, demonstrating 5.92% improvement on mathematical benchmarks and fixing 59.4% of final-answer corruption cases.