Score: 1

Exploring the Power of Diffusion Large Language Models for Software Engineering: An Empirical Investigation

Published: October 6, 2025 | arXiv ID: 2510.04605v1

By: Jingyao Zhang , Tianlin Li , Xiaoyu Zhang and more

Potential Business Impact:

Makes computers write and fix code faster.

Business Areas:
Natural Language Processing Artificial Intelligence, Data and Analytics, Software

Autoregressive Large Language Models (AR-LLMs) are widely used in software engineering (SE) but face limitations in processing code structure information and suffer from high inference latency. Diffusion LLMs (DLLMs) offer a promising alternative with global bidirectional encoding and decoupled generation steps. This work presents the first comprehensive evaluation of DLLMs across the software development lifecycle, including code generation, defect detection, and program repair. On a large-scale benchmark of 52,937 tasks, 7Bparameter DLLMs outperform AR-LLMs with a 30% average accuracy improvement achieving a 113% gain on cross-file repair, while maintaining superior efficiency and reduced latency. Our results establish DLLMs as a superior paradigm for SE tasks.

Country of Origin
πŸ‡ΈπŸ‡¬ πŸ‡¨πŸ‡³ China, Singapore

Page Count
5 pages

Category
Computer Science:
Software Engineering