Rethinking the Generation Order of Block Diffusion Language Models
Mirrored from arXiv — NLP / Computation & Language for archival readability. Support the source by reading on the original site.
Computer Science > Computation and Language
Title:Rethinking the Generation Order of Block Diffusion Language Models
Abstract:Diffusion language models enable flexible arbitrary-order generation, but existing sampling methods are mostly designed for early masked diffusion models (MDMs). In this work, we study sampling for recent block diffusion language models (BDLMs). We show empirically and analytically that these models are naturally more aligned with left-to-right decoding than MDMs. Based on this observation, we propose Parallel Autoregressive Decoding (PARD), a simple training-free sampling method that preserves left-to-right unmasking structure while allowing parallel token commitment. Extensive experiments show that PARD consistently outperforms existing parallel samplers in generation quality, while achieving substantial speedups over pure AR decoding with only a small quality gap.
| Comments: | 20 pages, 15 figures, 6 tables |
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2607.24306 [cs.CL] |
| (or arXiv:2607.24306v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2607.24306
arXiv-issued DOI via DataCite (pending registration)
|
Access Paper:
- View PDF
- TeX Source
References & Citations
Bookmark
Bibliographic and Citation Tools
Code, Data and Media Associated with this Article
Demos
Recommenders and Search Tools
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
More from arXiv — NLP / Computation & Language
-
Latent Fact-Checking: Detecting Misinformation through Activation Engineering
Aug 10
-
Quantization Damage Is Multiplicative, Not Additive
Aug 10
-
Modular TTT: Rethinking Test-Time Training as Composable Modules
Aug 10
-
Trajectory-Relative Hindsight Distillation for Agentic Reinforcement Learning
Aug 10
Discussion (0)
Sign in to join the discussion. Free account, 30 seconds — email code or GitHub.
Sign in →No comments yet. Sign in and be the first to say something.