@inproceedings{liu-etal-2025-deeprtl2,
    title = "{D}eep{RTL}2: A Versatile Model for {RTL}-Related Tasks",
    author = "Liu, Yi  and
      Zhang, Hongji  and
      Zhou, Yunhao  and
      Shi, Zhengyuan  and
      Xu, Changran  and
      Xu, Qiang",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/corrections-2025-08/2025.findings-acl.336/",
    doi = "10.18653/v1/2025.findings-acl.336",
    pages = "6485--6500",
    ISBN = "979-8-89176-256-5",
    abstract = "The integration of large language models (LLMs) into electronic design automation (EDA) has significantly advanced the field, offering transformative benefits, particularly in register transfer level (RTL) code generation and understanding. While previous studies have demonstrated the efficacy of fine-tuning LLMs for these generation-based tasks, embedding-based tasks, which are equally critical to EDA workflows, have been largely overlooked. These tasks, including natural language code search, RTL code functionality equivalence checking, and performance prediction, are essential for accelerating and optimizing the hardware design process. To address this gap, we present $\textbf{DeepRTL2}$, a family of versatile LLMs that unifies both generation- and embedding-based tasks related to RTL. By simultaneously tackling a broad range of tasks, DeepRTL2 represents the first model to provide a comprehensive solution to the diverse challenges in EDA. Through extensive experiments, we show that DeepRTL2 achieves state-of-the-art performance across all evaluated tasks."
}