עבר את הגבולות: עריכה מרוב-בלוק למודלי שפה גדולי-התפשטות

תקציר מקורי באנגליתarXiv:2607.22663v2 Announce Type: replace Abstract: Block diffusion is the dominant approach for scaling discrete diffusion language models (dLLMs), as fixed-size blocks preserve parallel decoding while keeping quadratic attention costs tractable. Yet blockwise generation creates a structural weakness: tokens near a block boundary lack future cross-block context, and errors in finalized blocks become irreversible context for later generation. We call this the block boundary problem. Measuring predictions with and without later-block context shows that boundary sensitivity rises sharply: on AIME 2025, mean self-containedness divergence (SCD) in the last quarter of a block is 61.3 times that in the first quarter. We propose Multi-Block Editing (MBE), which revises decoded tokens using cross-