SOURCE-LINKED INTELLIGENCE

In-Place Instruction Following in Diffusion Language Models

arXiv · AI, language, vision and robotics · article · Sep 7, 2026 · UTC

Diffusion Large Language Models (dLLMs) generate text via bidirectional iterative denoising, naturally supporting user-specified constraints anchored at arbitrary output positions, a paradigm known as In-place Prompting (IPP). We formalize this as the In-place Instruction Following (IIF) task and construct IIF-Bench, a hierarchical benchmark spanning literal, style, and discourse-function constraints, paired with a rubric-based local-global evaluation protocol. An inference-time attention-bias probe suggests that vanilla dLLMs often under-prioritize constraint spans during denoising. We then p

Read original source ↗ Open in workspace

recordType

paper

region

Global