Revise, Don't Freeze: Sampler-Matched Training for Self-Correcting Masked 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:Revise, Don't Freeze: Sampler-Matched Training for Self-Correcting Masked Diffusion Language Models
Abstract:Masked diffusion language models (MDLMs) re-predict every position at each denoising step, but standard samplers commit tokens once revealed, leaving this revision capability unused. Existing approaches either add heuristic or learned mechanisms to revise committed tokens, or remask them back to [MASK] before re-predicting; a principled sampler that directly revises visible tokens without auxiliary modules remains underexplored. We introduce D3IM, a parameter-free sampler derived as a corrector-style reverse update that permits direct visible-to-visible revision without additional modules or auxiliary passes. D3IM also reveals a model-side obstacle we term preservation bias: the model tends to reproduce its own wrong committed tokens rather than correct them. We address this with SCOPE (Self-Conditioned On Prediction Errors), a lightweight post-training procedure that simulates D3IM's sampling process. On LLaDA-8B at 64 denoising steps, SCOPE+D3IM improves over the original LLaDA-8B with standard unmasking by +13.0 on GSM8K (68.3%), +4.8 on MATH-500 (23.6%), +15.3 on HumanEval (29.3%), and +10.4 on MBPP (30.8%), with gains that increase as more denoising steps are used on math and HumanEval.
| Comments: | 8 pages, 2 figures, 10 tables |
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2606.01026 [cs.CL] |
| (or arXiv:2606.01026v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2606.01026
arXiv-issued DOI via DataCite (pending registration)
|
Access Paper:
- View PDF
- HTML (experimental)
- 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
-
DraDDP: A Multimodal Multi-Party Dialogue Discourse Parsing Dataset
Jun 2
-
Toward Robust In-Context Learning: Leveraging Out-of-distribution Proxies for Target Inaccessible Demonstration Retrieval
Jun 2
-
AEyeDE: An Attention-Based Attribution Framework for AI-Generated Text Detection
Jun 2
-
CSRP: Chain-of-Thought Reasoning for Chinese Text Correction via Reinforcement Learning with Efficiency-Aware Rewards
Jun 2
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.