While large language models (LLMs) have demonstrated the ability to generate hardware description language (HDL) code for digital circuits, they still suffer from the hallucination problem, which leads to the generation of incorrect HDL code or misunderstanding of specifications. In this work, we introduce a human-expert-inspired method to mitigate the hallucination of LLMs and improve the performance in HDL code generation. We first let LLMs classify the type of the circuit based on the specifications. Then, according to the type of the circuit, we split the tasks into several sub-procedures, including information extraction and human-like design flow using Electronic Design Automation (EDA) tools. Besides, we also use a search method to mitigate the variation in code generation. Experimental results show that our method can significantly improve the functional correctness of the generated Verilog and reduce the hallucination of LLMs.
CodeV: Empowering LLMs with HDL Generation through Multi-Level Summarization
State Key Lab of Processors, Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所处理器重点实验室);University of Chinese Academy of Sciences(中国科学院大学);Cambricon Technologies(寒武科技);School of Information Science and Technology, ShanghaiTech University(上海科技大学信息科学与技术学院);University of Science and Technology of China(中国科学技术大学);Shanghai Innovation Center for Processor Technologies(上海处理器技术创新中心)
ReChisel: Effective Automatic Chisel Code Generation by LLM with Reflection
Department of Computer Science, City University of Hong Kong(香港城市大学计算机科学系);School of Computer Science and Engineering, Northeastern University(东北大学计算机科学与工程学院);School of Automation, Southeast University(东南大学自动化学院);National Center of Technology Innovation for EDA, China(中国EDA技术创新国家中心);School of Integrated Circuits, Southeast University(东南大学集成电路学院)
SecureRAG-RTL: A Retrieval-Augmented, Multi-Agent, Zero-Shot LLM-Driven Framework for Hardware Vulnerability Detection
School of Computing, Wichita State University(计算机科学学院,威斯康星州立大学);Department of Electrical and Computer Engineering, Auburn University(电气与计算机工程系,阿伯茨兰大学);IBM
KREL: Automatic Medical Coding via Knowledge-Guided Reasoning over Clinical Evidence with LLMs
The University of New South Wales(新南威尔士大学);University of Göttingen(哥廷根大学);Macquarie University(麦考瑞大学);Beijing Intelligent Decision Medical Technology Co. Ltd(北京智决医疗科技有限公司)
Cannot or Should Not? Automatic Analysis of Refusal Composition in IFT/RLHF Datasets and Refusal Behavior of Black-Box LLMs
Technical University of Munich(慕尼黑工业大学);University of Cambridge(剑桥大学);ETH Zurich(苏黎世联邦理工学院);Stanford University(斯坦福大学);TÜV Nord Mobility(北德集团移动事业部);Massachusetts Institute of Technology (MIT)(麻省理工学院)
FrontendBench: A Benchmark for Evaluating LLMs on Front-End Development via Automatic Evaluation
Institute for Clarity in Documentation(清晰文档研究所);Inria Paris-Rocquencourt(巴黎-罗quant研究所);Rajiv Gandhi University(拉贾·甘地大学);Tsinghua University(清华大学);Palmer Research Laboratories(帕尔默研究实验室)
QiMeng-TensorOp: Automatically Generating High-Performance Tensor Operators with Hardware Primitives
Institute of Software Chinese Academy of Sciences(中国科学院软件研究所);Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所);Peking University(北京大学)
ShadowCode: Towards (Automatic) External Prompt Injection Attack against Code LLMs
State Key Laboratory of Blockchain and Data Security, Zhejiang University(区块链与数据安全国家重点实验室,浙江大学);Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security, Hangzhou(杭州高新区(滨江)区块链与数据安全研究院,杭州);College of Computing and Data Science, Nanyang Technological University(计算与数据科学学院,南洋理工大学)