AssertCoder: LLM-Based Assertion Generation via Multimodal Specification Extraction

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Tian, Enyuan, Ci, Yiwei, Yang, Qiusong, Li, Yufeng, Lyu, Zhichao
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912481741373440
author Tian, Enyuan
Ci, Yiwei
Yang, Qiusong
Li, Yufeng
Lyu, Zhichao
author_facet Tian, Enyuan
Ci, Yiwei
Yang, Qiusong
Li, Yufeng
Lyu, Zhichao
contents Assertion-Based Verification (ABV) is critical for ensuring functional correctness in modern hardware systems. However, manually writing high-quality SVAs remains labor-intensive and error-prone. To bridge this gap, we propose AssertCoder, a novel unified framework that automatically generates high-quality SVAs directly from multimodal hardware design specifications. AssertCoder employs a modality-sensitive preprocessing to parse heterogeneous specification formats (text, tables, diagrams, and formulas), followed by a set of dedicated semantic analyzers that extract structured representations aligned with signal-level semantics. These representations are utilized to drive assertion synthesis via multi-step chain-of-thought (CoT) prompting. The framework incorporates a mutation-based evaluation approach to assess assertion quality via model checking and further refine the generated assertions. Experimental evaluation across three real-world Register-Transfer Level (RTL) designs demonstrates AssertCoder's superior performance, achieving an average increase of 8.4% in functional correctness and 5.8% in mutation detection compared to existing state-of-the-art approaches.
format Preprint
id arxiv_https___arxiv_org_abs_2507_10338
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle AssertCoder: LLM-Based Assertion Generation via Multimodal Specification Extraction
Tian, Enyuan
Ci, Yiwei
Yang, Qiusong
Li, Yufeng
Lyu, Zhichao
Software Engineering
Hardware Architecture
Logic in Computer Science
Assertion-Based Verification (ABV) is critical for ensuring functional correctness in modern hardware systems. However, manually writing high-quality SVAs remains labor-intensive and error-prone. To bridge this gap, we propose AssertCoder, a novel unified framework that automatically generates high-quality SVAs directly from multimodal hardware design specifications. AssertCoder employs a modality-sensitive preprocessing to parse heterogeneous specification formats (text, tables, diagrams, and formulas), followed by a set of dedicated semantic analyzers that extract structured representations aligned with signal-level semantics. These representations are utilized to drive assertion synthesis via multi-step chain-of-thought (CoT) prompting. The framework incorporates a mutation-based evaluation approach to assess assertion quality via model checking and further refine the generated assertions. Experimental evaluation across three real-world Register-Transfer Level (RTL) designs demonstrates AssertCoder's superior performance, achieving an average increase of 8.4% in functional correctness and 5.8% in mutation detection compared to existing state-of-the-art approaches.
title AssertCoder: LLM-Based Assertion Generation via Multimodal Specification Extraction
topic Software Engineering
Hardware Architecture
Logic in Computer Science
url https://arxiv.org/abs/2507.10338