VerilogCL: A Contrastive Learning Framework for Robust LLM-Based Verilog Generation

TL;DR

VerilogCL is a contrastive learning framework that improves the accuracy and reliability of LLM-generated Verilog code by learning to distinguish correct from erroneous designs and proactively filtering low-confidence outputs.

Contribution

It introduces a novel contrastive learning approach with minimal-error data augmentation and a proactive screening module for robust Verilog code generation.

Findings

Outperforms baselines in compilation success rate.

Achieves higher functional correctness on benchmarks.

Enhances separation between correct and erroneous code in representation space.

Abstract

Large Language Models (LLMs) have recently achieved strong performance in software code generation. However, applying them to hardware description languages (HDLs), such as Verilog, remains challenging because high-quality training data are relatively scarce. In practice, LLM-generated Verilog often contains syntactic or structural errors that either cause compilation failures or produce functionally incorrect designs, which limit its reliability in hardware design workflows. In this work, we propose VerilogCL, an integrated framework that enhances Verilog code generation by explicitly learning the boundary between correct and erroneous RTL through contrastive learning and proactive error screening. Our approach introduces minimal-error data augmentation, generating paired training samples of correct RTL and minimally perturbed erroneous RTL to teach the model to recognize fine-grained distinctions between correct and erroneous code. We then apply contrastive learning to learn a clearer validity boundary in the representation space, improving the separation between correct and erroneous RTL code. In addition, we introduce a proactive screening module that combines semantic embeddings with token-level uncertainty features to filter low-confidence candidates during generation. Experiments on public benchmarks, including VerilogEval and RTLLM, show that our 7B-parameter model outperforms the evaluated open-source, Verilog-specialized, and commercial baselines in both compilation success rate and functional correctness.