Оригинальная аннотация: 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
Полезно для: Подход применим к диффузионным большим языковым моделям, поддерживающим пользовательские ограничения в произвольных позициях вывода. · Ограничение: При денойзинге обычные dLLM часто недостаточно приоритизируют участки с ограничениями.
Оригинальная аннотация: Autoregressive language models commit one token per forward pass; diffusion language models commit a block of tokens over several steps. We ask whether a block can be committed in a single forward pass. We study this with a noise-conditioned masked denoiser: a data-independent Gaussian noise field is added to the mask embeddings so that, in principle, each sampled field selects one joint mode of the block. The established way of training such a model is to sample several fields per example and let them compete for the data, by winner-take-all or importance weighting. This gives the noise only
Полезно для: Метод применим к генерации блоков за один шаг с одним прямым проходом на блок. · Ограничение: Источник не приводит количественных результатов и не уточняет размеры протестированных моделей.