遵循潜在路线图：用锚点词元为扩散大语言模型实现可撤销解码

Computer Science > Computation and Language arXiv:2606.16847 (cs) [Submitted on 15 Jun 2026 (v1), last revised 16 Sep 2026 (this version, v5)] Title:Follow the Latent Roadmap: Navigating Revocable Decoding for Diffusion LLMs with Anchor Tokens Authors:Yizhen Yao, Qinglin Zhu, Runcong Zhao, Xiangxiang Dai, Yanzheng Xiang, Yulan He, Lin Gui View a PDF of the paper titled Follow the Latent Roadmap: Navigating Revocable Decoding for Diffusion LLMs with Anchor Tokens, by Yizhen Yao and 6 other authors View PDF HTML (experimental) Abstract:Diffusion Large Language Models (dLLMs) offer a promising avenue for parallel generation but face a trade-off between decoding speed and quality. While revocable decoding strategies attempt to mitigate errors by verifying and remasking tokens, they typically operate within a mixed-quality context. This leads to two critical failures: \textit{Error Propagation}, where new tokens absorb toxic information from erroneous context, and \textit{Local Error Reinforcement}, where errors mutually reinforce each other to evade detection. To alleviate these challenges, we propose ASRD (Anchor Supervised Revocable Decoding), a training-free framework that operates within the embedding space. ASRD explicitly decouples the decoding context into trusted \textit{Anchor Tokens}, which are identified via temporal consistency, and uncertain candidates. Leveraging a dynamic Anchor Tokens Cache, we introduce two complementary mechanisms: (1) Anchor-Guided Generation, which injects entropy-weighted anchor signals into masked positions to implicitly rectify attention toward the reliable global skeleton; and (2) Anchor-Perturbed Verification, which applies orthogonal perturbations to uncertain candidate tokens, destabilizing and remasking errors driven by fragile local consensus. Extensive experiments on math and coding benchmarks demonstrate that ASRD outperforms recent remasking baselines, achieving accuracy improvements of up to 6.4\% while accelerating inference throughput by up to 7.2$\times$.The code is available at this https URL. Comments: Subjects: Computation and Language (cs.CL); Artificial Intelligence (cs.AI) Cite as: arXiv:2606.16847 [cs.CL] (or arXiv:2606.16847v5 [cs.CL] for this version) https://doi.org/10.48550/arXiv.2606.16847 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Yizhen Yao [view email] [v1] Mon, 15 Jun 2026 15:23:47 UTC (604 KB) [v2] Sat, 20 Jun 2026 11:33:42 UTC (604 KB) [v3] Tue, 14 Jul 2026 09:40:22 UTC (604 KB) [v4] Wed, 2 Sep 2026 11:15:54 UTC (696 KB) [v5] Wed, 16 Sep 2026 12:28:19 UTC (697 KB) Full-text links: Access Paper: View a PDF of the paper titled Follow the Latent Roadmap: Navigating Revocable Decoding for Diffusion LLMs with Anchor Tokens, by Yizhen Yao and 6 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.CL new | recent | 2026-06 Change to browse by: cs cs.AI References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: 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?)