用大模型自动设计有限状态机，提升成功率。
Enhancing Finite State Machine Design Automation with Large Language Models and Prompt Engineering Techniques
- 采用指令式提示和新提示优化方法，增强模型生成能力。
- 三款大模型在不同场景下成功率达60%-85%。
- 适合硬件设计自动化研究者与工程师参考。
近年来，大语言模型（LLMs）因其与硬件描述语言（HDL）的良好兼容性受到广泛关注。本文评估了Claude 3 Opus、ChatGPT-4和ChatGPT-4o在有限状态机（FSM）设计任务中的表现，基于HDLBits提供的教学内容，分析其稳定性、局限性及提升路径。进一步探索了‘待办导向提示法’（TOP Patch）对不同设计场景下模型成功率的影响。实验结果表明，系统化提示格式与新型提示优化方法具有潜力，可拓展至其他领域，未来有望与其他提示工程技术融合应用。
原文摘要 · Abstract (English)
Large Language Models (LLMs) have attracted considerable attention in recent years due to their remarkable compatibility with Hardware Description Language (HDL) design. In this paper, we examine the performance of three major LLMs, Claude 3 Opus, ChatGPT-4, and ChatGPT-4o, in designing finite state machines (FSMs). By utilizing the instructional content provided by HDLBits, we evaluate the stability, limitations, and potential approaches for improving the success rates of these models. Furthermore, we explore the impact of using the prompt-refining method, To-do-Oriented Prompting (TOP) Patch, on the success rate of these LLM models in various FSM design scenarios. The results show that the systematic format prompt method and the novel prompt refinement method have the potential to be applied to other domains beyond HDL design automation, considering its possible integration with other prompt engineering techniques in the future.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。