Next Semantic Scale Prediction via Hierarchical Diffusion Language Models

• URL: http://arxiv.org/abs/2510.08632v1
• Date: Wed, 08 Oct 2025 17:41:12 GMT
• Title: Next Semantic Scale Prediction via Hierarchical Diffusion Language Models
• Authors: Cai Zhou, Chenyu Wang, Dinghuai Zhang, Shangyuan Tong, Yifei Wang, Stephen Bates, Tommi Jaakkola,
• Abstract summary: HDLM builds on a hierarchical vocabulary where low-level tokens with detailed semantics are surjectively mapped to high-level tokens with coarse-grained meanings.<n>In the forward process, each token is independently perturbed to its higher-level ancestor with more abstract semantics according to the scheduler.<n>In the reverse process the model progressively predicts the next, more detailed semantics.
• Score: 31.562156001116673
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In this paper we introduce Hierarchical Diffusion Language Models (HDLM) -- a novel family of discrete diffusion models for language modeling. HDLM builds on a hierarchical vocabulary where low-level tokens with detailed semantics are surjectively mapped to high-level tokens with coarse-grained meanings. In the forward process, each token is independently perturbed to its higher-level ancestor with more abstract semantics according to the scheduler, while in the reverse process the model progressively predicts the next, more detailed semantics. Taken together, HDLM provides a general time-varying next semantic scale prediction process for language modeling. We derive closed-form expressions for the diffusion Evidence Lower Bound (ELBO), and show that HDLM can be implemented in a flexible manner while including the existing MDLM as a special case. We also propose practical training techniques based on the insights. Extensive text generation experiments validate the effectiveness of HDLM, which demonstrates consistently lower validation and generative perplexity than baselines.

Related papers

• SemPA: Improving Sentence Embeddings of Large Language Models through Semantic Preference Alignment [21.557846771500426]
  SemPA boosts the sentence representations while preserving the generative ability of LLMs via semantic preference alignment.<n>We establish a formal connection between DPO and contrastive learning under the Plackett-Luce model framework.
  arXiv  Detail & Related papers  (2026-01-08T16:19:24Z)
• Adapting LLMs to Time Series Forecasting via Temporal Heterogeneity Modeling and Semantic Alignment [32.41581846555808]
  Large Language Models (LLMs) have recently demonstrated impressive capabilities in natural language processing.<n>We propose TALON, a unified framework that enhances LLM-based forecasting by modeling temporal and enforcing semantic alignment.<n>Experiments on seven real-world benchmarks demonstrate that TALON achieves superior performance across all datasets.
  arXiv  Detail & Related papers  (2025-08-10T06:06:19Z)
• Discrete Diffusion in Large Language and Multimodal Models: A Survey [61.86669998363359]
  We provide a systematic survey of Discrete Diffusion Language Models (dLLMs) and Discrete Diffusion Multimodal Language Models (dMLLMs)<n>Unlike autoregressive (AR) models, dLLMs and dMLLMs adopt a multi-token, parallel decoding paradigm using full attention and a denoising-based generation strategy.<n>We trace the historical development of dLLMs and dMLLMs, formalize the underlying mathematical frameworks, list commonly-used modeling methods, and categorize representative models.
  arXiv  Detail & Related papers  (2025-06-16T17:59:08Z)
• DLM-One: Diffusion Language Models for One-Step Sequence Generation [63.43422118066493]
  DLM-One is a score-distillation-based framework for one-step sequence generation with continuous diffusion language models.<n>We investigate whether DLM-One can achieve substantial gains in sampling efficiency for language modeling.
  arXiv  Detail & Related papers  (2025-05-30T22:42:23Z)
• Generative Multimodal Pretraining with Discrete Diffusion Timestep Tokens [66.02261367232256]
  Multimodal Large Language Models (MLLMs) aim to unify visual comprehension and generation.<n>Existing approaches rely on spatial visual tokens, where image patches are encoded and arranged according to a spatial order.<n>In this paper, we build a proper visual language by reconstructing diffusion timesteps to learn discrete visual tokens.
  arXiv  Detail & Related papers  (2025-04-20T16:14:28Z)
• Multimodal Latent Language Modeling with Next-Token Diffusion [111.93906046452125]
  Multimodal generative models require a unified approach to handle both discrete data (e.g., text and code) and continuous data (e.g., image, audio, video)<n>We propose Latent Language Modeling (LatentLM), which seamlessly integrates continuous and discrete data using causal Transformers.
  arXiv  Detail & Related papers  (2024-12-11T18:57:32Z)
• Fantastic Semantics and Where to Find Them: Investigating Which Layers of Generative LLMs Reflect Lexical Semantics [50.982315553104975]
  We investigate the bottom-up evolution of lexical semantics for a popular large language model, namely Llama2. Our experiments show that the representations in lower layers encode lexical semantics, while the higher layers, with weaker semantic induction, are responsible for prediction. This is in contrast to models with discriminative objectives, such as mask language modeling, where the higher layers obtain better lexical semantics.
  arXiv  Detail & Related papers  (2024-03-03T13:14:47Z)
• Guiding the PLMs with Semantic Anchors as Intermediate Supervision: Towards Interpretable Semantic Parsing [57.11806632758607]
  We propose to incorporate the current pretrained language models with a hierarchical decoder network. By taking the first-principle structures as the semantic anchors, we propose two novel intermediate supervision tasks. We conduct intensive experiments on several semantic parsing benchmarks and demonstrate that our approach can consistently outperform the baselines.
  arXiv  Detail & Related papers  (2022-10-04T07:27:29Z)
• Masked Language Modeling and the Distributional Hypothesis: Order Word Matters Pre-training for Little [74.49773960145681]
  A possible explanation for the impressive performance of masked language model (MLM)-training is that such models have learned to represent the syntactic structures prevalent in NLP pipelines. In this paper, we propose a different explanation: pre-trains succeed on downstream tasks almost entirely due to their ability to model higher-order word co-occurrence statistics. Our results show that purely distributional information largely explains the success of pre-training, and underscore the importance of curating challenging evaluation datasets that require deeper linguistic knowledge.
  arXiv  Detail & Related papers  (2021-04-14T06:30:36Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.