理解并缓解LLM生成的RTL代码错误
Understanding and Mitigating Errors of LLM-Generated RTL Code
AI总结：
本文提出基于LLM的框架，通过检索增强生成、规则检查、多模态转换和迭代仿真调试，显著提升了RTL代码生成的准确性。
摘要：
尽管在基于大型语言模型（LLM）的寄存器传输级（RTL）代码生成方面取得有限成功，但错误的根本原因仍缺乏深入理解。为此，我们进行了全面的错误分析，发现大多数失败并非源于推理不足，而是由于缺乏RTL编程知识、电路理解不足、规范模糊或多模态输入的误解。利用上下文学习，我们提出针对性的纠正技术：一个检索增强生成（RAG）知识库以提供领域专业知识；设计描述规则与规则检查以澄清输入；外部工具将多模态数据转换为LLM兼容格式；以及用于剩余错误的迭代仿真调试循环。将这些整合到基于LLM的框架中，实现了显著提升，在VerilogEval基准测试中使用DeepSeek-v3.2-Speciale达到98.1%的准确率，证明了我们方法的有效性。
英文摘要：
Despite limited success in large language model (LLM)-based register-transfer-level (RTL) code generation, the root causes of errors remain poorly understood. To address this, we conduct a comprehensive error analysis, finding that most failures arise not from deficient reasoning, but from a lack of RTL programming knowledge, insufficient circuit understanding, ambiguous specifications, or misinterpreted multimodal inputs. Leveraging in-context learning, we propose targeted correction techniques: a retrieval-augmented generation (RAG) knowledge base to supply domain expertise; design description rules with rule-checking to clarify inputs; external tools to convert multimodal data into LLM-compatible formats; and an iterative simulation-debugging loop for remaining errors. Integrating these into an LLM-based framework yields significant improvement, achieving 98.1% accuracy on the VerilogEval benchmark with DeepSeek-v3.2-Speciale, demonstrating the effectiveness of our approach.
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。
