ChipExpert:开源的集成电路设计专用大语言模型
ChipExpert: The Open-Source Integrated-Circuit-Design-Specific Large Language Model
AI总结:
本文提出首个开源IC设计专用大语言模型ChipExpert,基于Llama-3 8B,通过定制数据训练、偏好对齐和RAG系统提升专业问答能力,并发布ChipICD-Bench基准验证其在IC设计子领域的专业表现。
摘要:
集成电路(IC)设计领域高度专业化,存在显著的进入壁垒以及研发挑战。尽管大语言模型(LLMs)已在众多领域取得显著成功,但现有LLMs往往无法满足学生、工程师和研究人员的特定需求,因此LLMs在IC设计领域的潜力仍基本未被探索。为解决这些问题,我们提出ChipExpert,这是首个专为IC设计领域量身定制的开源指令型LLM。ChipExpert基于当前最佳的开源基础模型之一(Llama-3 8B)进行训练。整个训练流程包括数据准备、继续预训练、指令引导的有监督微调、偏好对齐和评估等关键阶段。在数据准备阶段,我们通过人工筛选和数据合成技术构建了多个高质量定制数据集。在随后的两个阶段中,ChipExpert获取大量IC设计知识,并学习如何专业地回应用户查询。ChipExpert还经过一个对齐阶段,使用直接偏好优化(Direct Preference Optimization)以达到高标准的伦理表现。最后,为缓解ChipExpert的幻觉问题,我们基于IC设计知识库开发了检索增强生成(RAG)系统。我们还发布了首个IC设计基准ChipICD-Bench,用于评估LLMs在多个IC设计子领域中的能力。通过在该基准上开展的综合实验,ChipExpert在IC设计知识问答任务中展现出高水平的专业性。
英文摘要:
The field of integrated circuit (IC) design is highly specialized, presenting significant barriers to entry and research and development challenges. Although large language models (LLMs) have achieved remarkable success in various domains, existing LLMs often fail to meet the specific needs of students, engineers, and researchers. Consequently, the potential of LLMs in the IC design domain remains largely unexplored. To address these issues, we introduce ChipExpert, the first open-source, instructional LLM specifically tailored for the IC design field. ChipExpert is trained on one of the current best open-source base model (Llama-3 8B). The entire training process encompasses several key stages, including data preparation, continue pre-training, instruction-guided supervised fine-tuning, preference alignment, and evaluation. In the data preparation stage, we construct multiple high-quality custom datasets through manual selection and data synthesis techniques. In the subsequent two stages, ChipExpert acquires a vast amount of IC design knowledge and learns how to respond to user queries professionally. ChipExpert also undergoes an alignment phase, using Direct Preference Optimization, to achieve a high standard of ethical performance. Finally, to mitigate the hallucinations of ChipExpert, we have developed a Retrieval-Augmented Generation (RAG) system, based on the IC design knowledge base. We also released the first IC design benchmark ChipICD-Bench, to evaluate the capabilities of LLMs across multiple IC design sub-domains. Through comprehensive experiments conducted on this benchmark, ChipExpert demonstrated a high level of expertise in IC design knowledge Question-and-Answer tasks.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。