用轻量LLM+LoRA快速生成符合硬件逻辑的测试断言
AutoAssert 1: A LoRA Fine-Tuned LLM Model for Efficient Automated Assertion Generation
- 基于HDL与可调参轻量LLM结合LoRA微调生成断言
- 在不牺牲精度前提下显著降低训练成本
- 适合硬件验证与自动化测试开发者使用
随着软件系统复杂度持续提升，自动化测试与维护工具的需求呈指数增长。为应对这一迫切需求，本文提出一种基于硬件描述语言（HDL）的新型断言生成方法。该方法结合轻量级、参数可调的大型语言模型（LLM）与Unsloth平台，自动生成功能符合硬件逻辑的测试用例，显著降低训练成本，同时保持准确性和泛化性能。实证评估表明，该方法可高效生成严格符合硬件逻辑的断言。本框架为现代软件测试与维护挑战提供了稳健且灵活的解决方案。源代码位于：https://github.com/liusu-orange/AutoAssert-1 与 https://gitee.com/OpenBPU/auto-assert1。
原文摘要 · Abstract (English)
As the complexity of software systems continues to increase, the demand for automated testing and maintenance tools is growing exponentially. To meet this urgent need, we propose a new assertion generation method based on Hardware Description Language (HDL). This method combines a lightweight, parameter-adjustable large language model (LLM) with the Unsloth platform to automatically generate test cases, thereby significantly reducing training costs without sacrificing accuracy or generalization performance. Empirical evaluation shows that our method can efficiently generate assertions that strictly conform to the hardware logic. This framework provides a robust and flexible solution to modern software testing and maintenance challenges. https://github.com/liusu-orange/AutoAssert-1 and https://gitee.com/OpenBPU/auto-assert1 are the locations of the source code.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。