VeriGRAG: Enhancing LLM-Based Verilog Code Generation with Structure-Aware Soft Prompts
This addresses the problem of generating functionally and syntactically correct hardware code for engineers, representing a domain-specific incremental improvement.
The paper tackles the challenge of leveraging structural information in Verilog code to improve LLM-based generation, achieving state-of-the-art performance on benchmarks like VerilogEval and RTLLM.
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.