AssertMiner: Module-Level Spec Generation and Assertion Mining using Static Analysis Guided LLMs

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lyu, Hongqin, Wang, Yonghao, Zhou, Jiaxin, Chao, Zhiteng, Wang, Tiancheng, Li, Huawei
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908650285563904
author Lyu, Hongqin
Wang, Yonghao
Zhou, Jiaxin
Chao, Zhiteng
Wang, Tiancheng
Li, Huawei
author_facet Lyu, Hongqin
Wang, Yonghao
Zhou, Jiaxin
Chao, Zhiteng
Wang, Tiancheng
Li, Huawei
contents Assertion-based verification (ABV) is a key approach to checking whether a logic design complies with its architectural specifications. Existing assertion generation methods based on design specifications typically produce only top-level assertions, overlooking verification needs on the implementation details in the modules at the micro-architectural level, where design errors occur more frequently. To address this limitation, we present AssertMiner, a module-level assertion generation framework that leverages static information generated from abstract syntax tree (AST) to assist LLMs in mining assertions. Specifically, it performs AST-based structural extraction to derive the module call graph, I/O table, and dataflow graph, guiding the LLM to generate module-level specifications and mine module-level assertions. Our evaluation demonstrates that AssertMiner outperforms existing methods such as AssertLLM and Spec2Assertion in generating high-quality assertions for modules. When integrated with these methods, AssertMiner can enhance the structural coverage and significantly improve the error detection capability, enabling a more comprehensive and efficient verification process.
format Preprint
id arxiv_https___arxiv_org_abs_2511_10007
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle AssertMiner: Module-Level Spec Generation and Assertion Mining using Static Analysis Guided LLMs
Lyu, Hongqin
Wang, Yonghao
Zhou, Jiaxin
Chao, Zhiteng
Wang, Tiancheng
Li, Huawei
Hardware Architecture
Assertion-based verification (ABV) is a key approach to checking whether a logic design complies with its architectural specifications. Existing assertion generation methods based on design specifications typically produce only top-level assertions, overlooking verification needs on the implementation details in the modules at the micro-architectural level, where design errors occur more frequently. To address this limitation, we present AssertMiner, a module-level assertion generation framework that leverages static information generated from abstract syntax tree (AST) to assist LLMs in mining assertions. Specifically, it performs AST-based structural extraction to derive the module call graph, I/O table, and dataflow graph, guiding the LLM to generate module-level specifications and mine module-level assertions. Our evaluation demonstrates that AssertMiner outperforms existing methods such as AssertLLM and Spec2Assertion in generating high-quality assertions for modules. When integrated with these methods, AssertMiner can enhance the structural coverage and significantly improve the error detection capability, enabling a more comprehensive and efficient verification process.
title AssertMiner: Module-Level Spec Generation and Assertion Mining using Static Analysis Guided LLMs
topic Hardware Architecture
url https://arxiv.org/abs/2511.10007