Dystruct: Dynamically Structured Diffusion Language Model Decoding via Bayesian Inference

TL;DR

This paper introduces a training-free Bayesian structured decoding method for diffusion language models, enabling flexible-length, coherent text generation without retraining, and demonstrating significant improvements over existing methods.

Contribution

It proposes a novel Bayesian structured decoding framework that jointly infers sequence length, block boundaries, and decoding schedule, enhancing flexibility and quality in diffusion language models.

Findings

Significantly improves generation quality over fixed-length baselines.

Supports dynamic, flexible-length generation without retraining.

Demonstrates effectiveness across multiple benchmark datasets.

Abstract

Diffusion language models (DLMs) have recently emerged as a promising alternative to autoregressive models, primarily due to their ability to enable parallel decoding. Despite this advantage, most existing DLMs rely on a fixed generation length specified prior to decoding, which restricts their flexibility in real-world applications. While a few recent works attempt to support flexible-length generation, they typically suffer from notable limitations: some require costly retraining to accommodate variable-length outputs, while others depend solely on local confidence signals during decoding. Such local criteria fail to capture the evolving structure of the sequence, often resulting in suboptimal generation quality. In this paper, we propose a training-free, Bayesian structured decoding framework that formulates flexible-length generation as a dynamic structural inference problem. Our approach formulates flexible-length generation as a dynamic structural inference problem, jointly computing the expansion length, the block boundaries, and the decoding schedule. At each window expansion step, the method integrates local uncertainty with structural signals via a unified mechanism that supports dynamic structured generation, including both flexible block expansion and block organization, while maintaining coherence. Extensive experiments across multiple benchmarks demonstrate that our approach significantly improves generation quality and flexibility over existing fixed-length and flexible-length baselines. These results highlight the advantage of Bayesian structured decoding for diffusion language model, providing a principled and efficient solution for structured text generation.