Diffusion of Thoughts: Chain-of-Thought Reasoning in Diffusion Language Models
Refines intermediate reasoning representations over several rounds of denoising. A multi-pass version can revisit earlier parts of the reasoning as it refines the solution.
First public:
Cite this paper
Published version
Diffusion of Thought: Chain-of-Thought Reasoning in Diffusion Language Models
Jiacheng Ye, Shansan Gong, Liheng Chen, Lin Zheng, Jiahui Gao, Han Shi, Chuan Wu, Xin Jiang, Zhenguo Li, Wei Bi, Lingpeng Kong
Advances in Neural Information Processing Systems, 2024, pp. 105345-105374.
DOI: 10.52202/079017-3343
Checked 2026-10-18 against the publication record. The published title, author list or year can differ from the preprint.
Choose the version you used. The arXiv link may serve a revision; check the original paper for the exact result, assumptions and limitations you cite.
Method comparisons
Changing generation order or removing written steps
Diffusion of Thought changes how a chain of thought is generated: it refines the solution through denoising rather than committing to words strictly from left to right. This changes the generation schedule, not necessarily the visibility of the reasoning. The resulting chain can still be text, unlike methods that only emit the final answer.
Sources: Diffusion of Thought · Deng et al. (2024), §3
Paper details: Diffusion of Thoughts: Chain-of-Thought Reasoning in Diffusion Language Models · From Explicit CoT to Implicit CoT: Learning to Internalize CoT Step by Step
Explore this approach
Alternative generation methods — Change how intermediate steps are generated, revised, or searched—for example, by refining several steps in parallel. These are related approaches: some still produce written chains of thought.
Read or reuse this entry
Plain-text Markdown · JSON record · Find in the full list
Our summary and categories are a reading aid, not the authors’ abstract. Use the original paper for research claims. Suggest a correction.