VeriGRAG: Enhancing LLM-Based Verilog Code Generation with Structure-Aware Soft Prompts
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914100540342272 |
|---|---|
| author | Zhao, Jiayu Chen, Song |
| author_facet | Zhao, Jiayu Chen, Song |
| contents | Large language models (LLMs) have demonstrated strong capabilities in generating Verilog code from natural language descriptions. However, Verilog code inherently encodes structural information of hardware circuits. Effectively leveraging this structural information to enhance the functional and syntactic correctness of LLM-generated Verilog code remains a significant challenge. To address this challenge, we propose VeriGRAG , a novel framework that extracts structural graph embeddings from Verilog code using graph neural networks (GNNs). A multimodal retriever then selects the graph embeddings most relevant to the given generation task, which are aligned with the code modality through the VeriFormer module to generate structure-aware soft prompts. Our experiments demonstrate that VeriGRAG substantially improves the correctness of Verilog code generation, achieving state-of-the-art or superior performance across both VerilogEval and RTLLM benchmarks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_15914 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | VeriGRAG: Enhancing LLM-Based Verilog Code Generation with Structure-Aware Soft Prompts Zhao, Jiayu Chen, Song Hardware Architecture Artificial Intelligence Programming Languages Large language models (LLMs) have demonstrated strong capabilities in generating Verilog code from natural language descriptions. However, Verilog code inherently encodes structural information of hardware circuits. Effectively leveraging this structural information to enhance the functional and syntactic correctness of LLM-generated Verilog code remains a significant challenge. To address this challenge, we propose VeriGRAG , a novel framework that extracts structural graph embeddings from Verilog code using graph neural networks (GNNs). A multimodal retriever then selects the graph embeddings most relevant to the given generation task, which are aligned with the code modality through the VeriFormer module to generate structure-aware soft prompts. Our experiments demonstrate that VeriGRAG substantially improves the correctness of Verilog code generation, achieving state-of-the-art or superior performance across both VerilogEval and RTLLM benchmarks. |
| title | VeriGRAG: Enhancing LLM-Based Verilog Code Generation with Structure-Aware Soft Prompts |
| topic | Hardware Architecture Artificial Intelligence Programming Languages |
| url | https://arxiv.org/abs/2510.15914 |