Don't Commit Alone: Joint Token Commitment in Diffusion Language Models

[2607.04469] Don't Commit Alone: Joint Token Commitment in Diffusion Language Models Skip to main content Search Submit Donate Log in Computer Science > Computation and Language arXiv:2607.04469 (cs) [Submitted on 5 Jul 2026 ( v1 ), last revised 24 Aug 2026 (this version, v2)] Title: Don't Commit Alone: Joint Token Commitment in Diffusion Language Models Authors: Lin Yao View PDF HTML (experimental) Abstract: Diffusion language models (dLLMs) commit multiple tokens per denoising step by decoding each selected position independently from a shared context. When these positions are dependent, this factorization introduces an error captured by conditional total correlation, which confidence-based selection cannot infer from marginal probabilities alone. We propose CoCommit, a marker-gated coordination pass that delays commitment. After the usual bundle selection, a learned marker identifies the commit set, and the backbone's last n layers are re-applied to coordinate the marked positions before greedy argmax writes the tokens. This approximates joint-mode decoding while reusing existing weights, requiring only one partial forward pass and no auxiliary model. On LLaDA 2.1 with LoRA adapters and greedy inference, joint commitment improves five of the seven evaluated benchmarks over the released factorized decoder. The largest gains occur on code and reasoning tasks, while the remaining tasks are near parity. Subjects: Computation and Language (cs.CL) Cite as: arXiv:2607.04469 [cs.CL] (or arXiv:2607.04469v2 [cs.CL] for this version) https://doi.org/10.48550/arXiv.2607.04469 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Lin Yao [ view email ] [v1] Sun, 5 Jul 2026 19:29:13 UTC (1,022 KB) [v2] Mon, 24 Aug 2026 21:31:56 UTC (1,025 KB) Full-text links: Access Paper: View PDF HTML (experimental) TeX Source view license Current browse context: cs.CL < prev | next > new | recent | 2026-07 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs 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 . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• Don't Commit Alone: Joint Token Commitment in Diffusion Language Models#670669
• JUMP: Single-Pass Membership Inference on Fine-Tuned Diffusion Language Models#630080
• JUMP: Single-Pass Membership Inference on Fine-Tuned Diffusion Language Models#628218
• Membership Inference in Fine-tuned Diffusion Language Models via Token-level Memorization Asymmetry#627622
• The Shrinking Landscape of Linguistic Diversity in the Age of Large Language Models#670320