AutoAssert 1: A LoRA Fine-Tuned LLM Model for Efficient Automated Assertion Generation
This addresses the growing demand for automated testing tools in complex software systems, particularly for hardware logic, though it appears incremental as it builds on existing LLM and platform techniques.
The paper tackles the problem of automated assertion generation for hardware description languages by proposing a method that combines a lightweight LLM with the Unsloth platform, resulting in efficient generation of assertions that strictly conform to hardware logic while reducing training costs.
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.