Discrete Diffusion Language Models Are Training-Free Multi-Label Classifiers

[2608.14649] Discrete Diffusion Language Models Are Training-Free Multi-Label Classifiers Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Machine Learning arXiv:2608.14649 (cs) [Submitted on 30 Jul 2026] Title: Discrete Diffusion Language Models Are Training-Free Multi-Label Classifiers Authors: Pawan Kumar View a PDF of the paper titled Discrete Diffusion Language Models Are Training-Free Multi-Label Classifiers, by Pawan Kumar View PDF HTML (experimental) Abstract: We present dLLM-SetScore, a training-free method that uses discrete masked-diffusion language models for multi-label text classification. For each candidate label, it asks a short yes/no question and compares the probabilities of the two answer tokens at one masked position. The method uses no task-specific fine-tuning or training on textual-entailment datasets; a 200-example labelled validation slice selects thresholds, temperature, and prompt wording. We first show that placing all labels in one prompt creates a strong slot-position asymmetry: the first answer slot is predicted positive on $99.4\%$ of GoEmotions examples and $100\%$ of Reuters examples. Per-label scoring places every label in the same syntactic position, making predictions invariant to label order and avoiding this artifact. We evaluate LLaDA-8B and Dream-7B on six datasets against NLI models, an autoregressive LLM, SetFit, and supervised classifiers. On the five datasets shared by both diffusion families, Instruct checkpoints improve macro-F1 in 9 of 10 comparisons and micro-F1 in 8 of 10, although these comparisons do not identify the cause. Within our protocol, LLaDA-Instruct records the highest training-free values for both Reuters and ECtHR metrics. We prove permutation invariance, characterize thresholded decisions under weighted Hamming loss, and derive shortlist ceilings for recall and F1. An exploratory local Joint Set Refinement step lowers F1 from biased and unbiased initializations and is retained as a negative result. Comments: Accepted to SIAM SDM 2026, 39 pages Subjects: Machine Learning (cs.LG) Cite as: arXiv:2608.14649 [cs.LG] (or arXiv:2608.14649v1 [cs.LG] for this version) https://doi.org/10.48550/arXiv.2608.14649 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Pawan Kumar [ view email ] [v1] Thu, 30 Jul 2026 15:21:02 UTC (359 KB) Full-text links: Access Paper: View a PDF of the paper titled Discrete Diffusion Language Models Are Training-Free Multi-Label Classifiers, by Pawan Kumar View PDF HTML (experimental) TeX Source view license Current browse context: cs.LG < prev | next > new | recent | 2026-08 Change to browse by: cs 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? ) IArxiv recommender toggle IArxiv Recommender ( What is IArxiv? ) 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

• Looped Diffusion Language Models#224495
• AURORA-LM: Autoencoding Unified Representation for Continuous-Latent Diffusion Language Modeling#431399
• Less Uniform Discrete Diffusion is More Powerful and Scalable#1130659
• DA-DLM: Explicitly Modeling Token Dependencies in Diffusion Language Models#1084960
• VASTU: Language Models Struggle to Recognize Online Community Values#792691