{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,21]],"date-time":"2025-11-21T05:50:54Z","timestamp":1763704254171,"version":"3.45.0"},"reference-count":54,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,26]],"date-time":"2025-10-26T00:00:00Z","timestamp":1761436800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,26]],"date-time":"2025-10-26T00:00:00Z","timestamp":1761436800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,26]]},"DOI":"10.1109\/iccad66269.2025.11240644","type":"proceedings-article","created":{"date-parts":[[2025,11,20]],"date-time":"2025-11-20T18:39:34Z","timestamp":1763663974000},"page":"1-9","source":"Crossref","is-referenced-by-count":0,"title":["LLM4Verilog: Building Large-Scale, High-Quality Data Infrastructure for Verilog Code Generation via Community Efforts"],"prefix":"10.1109","author":[{"given":"Zhongzhi","family":"Yu","sequence":"first","affiliation":[{"name":"Georgia Institute of Technology"}]},{"given":"Chaojian","family":"Li","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology"}]},{"given":"Yongan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology"}]},{"given":"Mingjie","family":"Liu","sequence":"additional","affiliation":[{"name":"Nvidia Corporation"}]},{"given":"Nathaniel","family":"Pinckney","sequence":"additional","affiliation":[{"name":"Nvidia Corporation"}]},{"given":"Wenfei","family":"Zhou","sequence":"additional","affiliation":[{"name":"Nvidia Corporation"}]},{"given":"Rongjian","family":"Liang","sequence":"additional","affiliation":[{"name":"Nvidia Corporation"}]},{"given":"Haoyu","family":"Yang","sequence":"additional","affiliation":[{"name":"Nvidia Corporation"}]},{"given":"Haoxing","family":"Ren","sequence":"additional","affiliation":[{"name":"Nvidia Corporation"}]},{"given":"Yingyan Celine","family":"Lin","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology"}]}],"member":"263","reference":[{"article-title":"Codegen: An open large language model for code with multi-turn program synthesis","year":"2022","author":"Nijkamp","key":"ref1"},{"article-title":"Code4struct: Code generation for few-shot structured prediction from natural language","year":"2022","author":"Wang","key":"ref2"},{"article-title":"Scaling laws for neural language models","year":"2020","author":"Kaplan","key":"ref3"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD57390.2023.10323953"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/LAD62341.2024.10691738"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3643681"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD57390.2023.10323812"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ASP-DAC58780.2024.10473904"},{"article-title":"Wizardmath: Empowering mathematical reasoning for large language models via reinforced evol-instruct","year":"2023","author":"Luo","key":"ref9"},{"article-title":"Codexglue: A machine learning benchmark dataset for code understanding and generation","year":"2021","author":"Lu","key":"ref10"},{"article-title":"Betterv: Controlled verilog generation with discriminative guidance","year":"2024","author":"Pei","key":"ref11"},{"article-title":"Craftrtl: High-quality synthetic data generation for verilog code models with correct-by-construction non-textual representations and targeted code repair","year":"2024","author":"Liu","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/MLCAD65511.2025.11189212"},{"article-title":"ChipNeMo: Domain-Adapted LLMs for Chip Design","year":"2023","author":"Liu","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-industry.9"},{"article-title":"A survey on large language models for code generation","year":"2024","author":"Jiang","key":"ref16"},{"article-title":"Codesearchnet challenge: Evaluating the state of semantic code search","year":"2019","author":"Husain","key":"ref17"},{"key":"ref18","article-title":"The stack: 3 tb of permissively licensed source code","author":"Kocetkov","year":"2022","journal-title":"Preprint"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1108\/ws.2000.07949fab.004"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599790"},{"article-title":"Code llama: Open foundation models for code","year":"2023","author":"Roziere","key":"ref21"},{"article-title":"Deepseek-coder: When the large language model meets programming\u2013the rise of code intelligence","year":"2024","author":"Guo","key":"ref22"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-acl.1009"},{"article-title":"Evaluating large language models trained on code","year":"2021","author":"Chen","key":"ref24"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.49"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i1.32007"},{"article-title":"Chipgpt: How far are we from natural language hardware design","year":"2023","author":"Chang","key":"ref27"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/tcad.2025.3604320"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/LAD62341.2024.10691788"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3676536.3676830"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICLAD65226.2025.00013"},{"article-title":"The effects of data quality on machine learning performance","year":"2022","author":"Budach","key":"ref32"},{"key":"ref33","article-title":"Openassistant conversations-democratizing large language model alignment","volume":"36","author":"K\u00f6pf","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"author":"Kahng","key":"ref34","article-title":"Open-source eda birds-of-a-feather session at dac 2024 \u2014 open-source-eda-birds-of-a-feather"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.3758\/s13428-025-02804-1"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.24251\/HICSS.2022.548"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1080\/13658816.2019.1593422"},{"article-title":"Quality control challenges in crowdsourcing medical labeling","volume-title":"Proceedings of the SIGKDD Workshop on Data Collection, Curation, and Labeling for Mining and Learning (DCCL\u201919)","author":"Hutson","key":"ref38"},{"article-title":"Slimpajama-dc: Understanding data combinations for llm training","year":"2023","author":"Shen","key":"ref39"},{"author":"Williams","key":"ref40","article-title":"Icarus verilog \u2014 icarus verilog documentation"},{"key":"ref41","article-title":"Nemo: Build custom generative ai \u2014 nvidia"},{"key":"ref42","article-title":"Lambda: Gpu compute for ai"},{"article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","year":"2018","author":"Devlin","key":"ref43"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.139"},{"article-title":"Hdl-gpt: High-quality hdl is all you need","year":"2024","author":"Kumar","key":"ref45"},{"article-title":"Surveying the effects of quality, diversity, and complexity in synthetic data from large language models","year":"2024","author":"Havrilla","key":"ref46"},{"article-title":"A survey on data augmentation in large model era","year":"2024","author":"Zhou","key":"ref47"},{"issue":"99","key":"ref48","first-page":"3","article-title":"Icarus verilog: open-source verilog more than a year later","volume":"2002","author":"Williams","year":"2002","journal-title":"Linux Journal"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/SEQUEN.1997.666900"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.577"},{"key":"ref51","article-title":"Llm-based iterative hard example mining with boosting for academic question answering","author":"Zhou","year":"2024","journal-title":"KDD 2024 OAG-Challenge Cup"},{"article-title":"Take the bull by the horns: Hard sample-reweighted continual training improves llm generalization","year":"2024","author":"Chen","key":"ref52"},{"article-title":"Llama 2: Open foundation and fine-tuned chat models","year":"2023","author":"Touvron","key":"ref53"},{"article-title":"Qwen technical report","year":"2023","author":"Bai","key":"ref55"}],"event":{"name":"2025 IEEE\/ACM International Conference On Computer Aided Design (ICCAD)","start":{"date-parts":[[2025,10,26]]},"location":"Munich, Germany","end":{"date-parts":[[2025,10,30]]}},"container-title":["2025 IEEE\/ACM International Conference On Computer Aided Design (ICCAD)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11240608\/11240621\/11240644.pdf?arnumber=11240644","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,21]],"date-time":"2025-11-21T05:42:19Z","timestamp":1763703739000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11240644\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,26]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/iccad66269.2025.11240644","relation":{},"subject":[],"published":{"date-parts":[[2025,10,26]]}}}