IEEE

VeriLeaky: Navigating IP Protection vs Utility in Fine-Tuning for LLM-Driven Verilog Coding

Abstract: Large language models (LLMs) offer significant potential for coding, yet fine-tuning (FT) with curated data is essential for niche languages like Verilog. Using proprietary intellectual ...
IEEE

HaVen: Hallucination-Mitigated LLM for Verilog Code Generation Aligned with HDL Engineers

Abstract: Recently, the use of large language models (LLMs) for Verilog code generation has attracted great research interest to enable hardware design automation. However, previous works have shown a ...