Year: 2026
Type: preprint
Abstract: Diffusion language models (DLMs) generate text by iteratively denoising masked sequences, but standard decoding either fixes the sequence length or relies on ad hoc stopping rules, often leading to unnecessary denoising steps. We recast length selection as a discrete-time survival problem over the end-of-sequence token and propose a plug-in, training-free length predictor that can be added to any existing DLM. Across reasoning and code-generation benchmarks, survival-guided length decoding speeds up inference by up to 7 times while preserving task accuracy. We further find that predicted lengths vary widely even within the same dataset, making model performance sensitive to the chosen length.
Source: arXiv (Cornell University)
Authors: Kobyzev, Ivan, Ghaddar, Abbas, Cui, Yufei
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7204530481
Cites:
Cited by:
Related to: