Wrong Code, Right Structure: Learning Netlist Representations from Imperfect LLM-Generated RTL

ArXi:2603.09161v1 Announce Type: cross Learning effective netlist representations is fundamentally constrained by the scarcity of labeled datasets, as real designs are protected by Intellectual Property (IP) and costly to annotate. Existing work therefore focuses on small-scale circuits with clean labels, limiting scalability to realistic designs. Meanwhile, Large Language Models (LLMs) can generate Register-Transfer-Level (RTL) at scale, but their functional incorrectness has hindered their use in circuit analysis.