LLMs face significant challenges in Verilog generation due to limited domain-specific knowledge. While sampling techniques improve pass@k metrics, hardware engineers need one trustworthy solution rather than uncertain candidates. To bridge this gap, we formulate it as a semantic alignment problem between requirements and Verilog implementations, and propose VCD-RNK, a discriminator model tailored for efficient Verilog code reranking. Specifically, VCD-RNKincorporates Verilog-specific reasoning by distilling expert knowledge across three dimensions: code semantic analysis, test case generation, and functional correctness assessment. By explicitly simulating the above reasoning processes during inference, VCD-RNK effectively avoids computationally intensive test execution in existing methods.
@article{arxiv.2509.20215,
title = {The Cream Rises to the Top: Efficient Reranking Method for Verilog Code Generation},
author = {Guang Yang and Wei Zheng and Xiang Chen and Yifan Sun and Fengji Zhang and Terry Yue Zhuo},
journal= {arXiv preprint arXiv:2509.20215},
year = {2025}
}