{
  "id": "diffusion-language-model",
  "code": "PTL-0228",
  "term": "Diffusion Language Model",
  "aliases": [
    "diffusion LM",
    "DLM",
    "dLLM",
    "masked diffusion language model",
    "continuous diffusion language model",
    "CDLM"
  ],
  "category": "foundations",
  "definition": "A diffusion language model generates text by starting from a fully corrupted sequence, such as all mask tokens or noise over token embeddings, and refining the whole sequence over a series of denoising steps, instead of producing one token at a time from left to right.",
  "description": "There are two main families. Discrete diffusion models corrupt the tokens themselves, most often by replacing them with a mask token, and learn to restore them. Continuous diffusion models first map tokens to real-valued embeddings and add Gaussian-style noise to those. Diffusion-LM was an early continuous model aimed at controllable generation. LLaDA, a masked diffusion model trained from scratch at scale, performed comparably to autoregressive baselines, which suggested that strong language-model abilities do not depend on left-to-right generation. Because a diffusion model updates many positions in each step, it can produce several tokens per step and condition on text both before and after a position.",
  "example": null,
  "broader": [],
  "narrower": [],
  "related": [
    "large-language-model",
    "speculative-decoding",
    "foundation-model"
  ],
  "introduced": 2022,
  "added": "2026-10-27",
  "sources": [
    {
      "title": "Diffusion-LM Improves Controllable Text Generation",
      "authors": "Li et al.",
      "year": 2022,
      "url": "https://arxiv.org/abs/2205.14217"
    },
    {
      "title": "Large Language Diffusion Models",
      "authors": "Nie et al.",
      "year": 2025,
      "url": "https://arxiv.org/abs/2502.09992"
    },
    {
      "title": "Continuous diffusion language models",
      "authors": "Dieleman",
      "year": 2026,
      "url": "https://sander.ai/2026/08/24/continuous-dlms.html"
    }
  ],
  "url": "https://protologue.com/t/diffusion-language-model/",
  "citation": "Protologue. (2026). Diffusion Language Model. In Protologue: A Taxonomy of Prompting and LLM Techniques (v1.4.0, PTL-0228). https://protologue.com/t/diffusion-language-model/"
}