XGen-Q: An Explainable Domain-Adaptive LLM Framework with Retrieval-Augmented Generation for Software Security
Paper • 2510.19006 • Published
XGen-Q is a domain-adapted large language model designed for software security analysis and malware analysis. The model is built on Qwen/Qwen2.5-Coder-7B-Instruct. Also, the model pre-trained via SBAN dataset, that is a multi-dimensional malware dataset designed for LLM pretraining in software security.
@article{jelodar2025xgenq, title={XGen-Q: An Explainable Domain-Adaptive LLM Framework with Retrieval-Augmented Generation for Software Security}, author={Jelodar, Hamed and Meymani, Mohammad and Razavi-Far, Roozbeh and Ghorbani, Ali}, journal={arXiv preprint arXiv:2510.19006}, year={2025} }