# Diffusion Language Model

> 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.

- Identifier: PTL-0228
- Category: Foundations
- Canonical URL: https://protologue.com/t/diffusion-language-model/
- Also known as: diffusion LM, DLM, dLLM, masked diffusion language model, continuous diffusion language model, CDLM
- Introduced: 2022

## 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.

## Related terms

- [Large Language Model](https://protologue.com/t/large-language-model/)
- [Speculative Decoding](https://protologue.com/t/speculative-decoding/)
- [Foundation Model](https://protologue.com/t/foundation-model/)

## Sources

- Li et al. (2022). Diffusion-LM Improves Controllable Text Generation. https://arxiv.org/abs/2205.14217
- Nie et al. (2025). Large Language Diffusion Models. https://arxiv.org/abs/2502.09992
- Dieleman (2026). Continuous diffusion language models. https://sander.ai/2026/08/24/continuous-dlms.html

## Cite this entry

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/

License: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/)