{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T18:51:41Z","timestamp":1782845501444,"version":"3.54.5"},"reference-count":59,"publisher":"Association for Computing Machinery (ACM)","issue":"FSE","license":[{"start":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T00:00:00Z","timestamp":1782777600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Natural Science Research Start-up Foundation of Recruiting Talents of Nanjing University of Posts and Telecommunications","award":["NY22502"],"award-info":[{"award-number":["NY22502"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62371256"],"award-info":[{"award-number":["62371256"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Self-developed Project of Nanjing University of Posts and Telecommunications Nantong Research Institute Co., Ltd.","award":["ZY-001"],"award-info":[{"award-number":["ZY-001"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Proc. ACM Softw. Eng."],"published-print":{"date-parts":[[2026,6,30]]},"abstract":"<jats:p>With the increasing complexity and scale of integrated circuit (IC) designs, automated circuit design methods are essential for Verilog implementation. Although Large Language Models (LLMs) perform well in general-purpose coding such as C++ and Python, their performance in Verilog is constrained by domain-specific semantic and structural rules as well as the scarcity of high-quality training datasets. To address these issues, this work proposes a semantically enhanced Verilog code parsing and automatic repair framework based on Abstract Syntax Tree (AST). First, an advanced register-transfer level (RTL) analysis framework was developed to achieve semantic enhancement through static analysis\u2013driven functional role inference and attribute annotation. Second, enhanced AST information is used to construct structured prompts and generate semantically rich module descriptions via an Application Programming Interface (API) for dataset construction. Finally, an AST-guided automatic Verilog repair framework was designed, which leverages enhanced AST analysis for precise defect localization and intelligent repair through compiler feedback loops. Experimental results indicate that the proposed method successfully repaired 15.24% of defective Verilog code, resulting in a high-quality RTL benchmark dataset containing 318,021 samples. Models fine-tuned on this dataset demonstrate significant performance improvements across three benchmarks, achieving average improvements of 13.76% and 16.95% on Eval-Machine pass@1 and pass@5, 8.97% and 14.56% on Eval-Human pass@1 and pass@5, and 15.70% and 12.20% on RTLLM V1.1 Syntax-VCS and Func.<\/jats:p>","DOI":"10.1145\/3797073","type":"journal-article","created":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T17:06:14Z","timestamp":1782839174000},"page":"989-1010","source":"Crossref","is-referenced-by-count":0,"title":["VerilogASTBench: Benchmark Construction of Verilog AST Dataset with Dual-Stage AST Semantic Enhancement Framework"],"prefix":"10.1145","volume":"3","author":[{"ORCID":"https:\/\/2.zoppoz.workers.dev:443\/https\/orcid.org\/0009-0005-2695-8238","authenticated-orcid":false,"given":"Luping","family":"Zhang","sequence":"first","affiliation":[{"name":"Nanjing University of Posts and Telecommunications, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/2.zoppoz.workers.dev:443\/https\/orcid.org\/0009-0008-6151-3754","authenticated-orcid":false,"given":"Chao","family":"Chen","sequence":"additional","affiliation":[{"name":"Nanjing University of Posts and Telecommunications, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/2.zoppoz.workers.dev:443\/https\/orcid.org\/0009-0007-2344-8210","authenticated-orcid":false,"given":"Dapeng","family":"Yan","sequence":"additional","affiliation":[{"name":"Nanjing University of Posts and Telecommunications, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/2.zoppoz.workers.dev:443\/https\/orcid.org\/0000-0003-2081-555X","authenticated-orcid":false,"given":"Hui","family":"Xu","sequence":"additional","affiliation":[{"name":"Institute for Advanced Study, University of Electronic Science and Technology of China, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/2.zoppoz.workers.dev:443\/https\/orcid.org\/0000-0003-0691-2724","authenticated-orcid":false,"given":"Mingsheng","family":"Cao","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/2.zoppoz.workers.dev:443\/https\/orcid.org\/0000-0002-2549-8322","authenticated-orcid":false,"given":"Jingkuan","family":"Song","sequence":"additional","affiliation":[{"name":"Tongji University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/2.zoppoz.workers.dev:443\/https\/orcid.org\/0000-0002-0264-3849","authenticated-orcid":false,"given":"Zhikuang","family":"Cai","sequence":"additional","affiliation":[{"name":"Nanjing University of Posts and Telecommunications, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/2.zoppoz.workers.dev:443\/https\/orcid.org\/0000-0002-1490-986X","authenticated-orcid":false,"given":"Yufeng","family":"Guo","sequence":"additional","affiliation":[{"name":"Nanjing University of Posts and Telecommunications, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,30]]},"reference":[{"key":"e_1_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2303.08774"},{"key":"e_1_2_1_2_1","doi-asserted-by":"publisher","unstructured":"Jinze Bai Shuai Bai Yunfei Chu Zeyu Cui Kai Dang Xiaodong Deng Fei Huang et al. 2023. Qwen technical report. arXiv:2309.16609 [cs.CL] doi:10.48550\/arXiv.2309.16609 10.48550\/arXiv.2309.16609","DOI":"10.48550\/arXiv.2309.16609"},{"key":"e_1_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/3468"},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2507.13369"},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3649329"},{"key":"e_1_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2107.03374"},{"key":"e_1_2_1_7_1","volume-title":"Workshop on Open-Source EDA Technology (WOSET). https:\/\/2.zoppoz.workers.dev:443\/https\/woset-workshop.github.io\/PDFs\/2020\/a10","author":"Dargelas Alain","year":"2020","unstructured":"Alain Dargelas and Henner Zeller. 2020. Universal hardware data model. In Workshop on Open-Source EDA Technology (WOSET). https:\/\/2.zoppoz.workers.dev:443\/https\/woset-workshop.github.io\/PDFs\/2020\/a10.pdf"},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/SOCC66126.2025.11235413"},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW63119.2024.00034"},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CNCIT56797.2022.00036"},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3386337"},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCD63220.2024.00033"},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00354-"},{"key":"e_1_2_1_14_1","doi-asserted-by":"publisher","unstructured":"Emil Goh Maoyang Xiang I Wey T Teo et al. 2024. From english to asic: Hardware implementation with large language model. arXiv:2403.07039 [cs.AR] doi:10.48550\/arXiv.2403.07039 10.48550\/arXiv.2403.07039","DOI":"10.48550\/arXiv.2403.07039"},{"key":"e_1_2_1_15_1","unstructured":"Google. 2024. CodeGemma 7B (Hugging Face). https:\/\/2.zoppoz.workers.dev:443\/https\/huggingface.co\/google\/codegemma-7b"},{"key":"e_1_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/IRDS54852.2021.00013"},{"key":"e_1_2_1_17_1","doi-asserted-by":"publisher","unstructured":"Daya Guo Qihao Zhu Dejian Yang Zhenda Xie Kai Dong Wentao Zhang Guanting Chen Xiao Bi Yu Wu et al. 2024. DeepSeek-Coder: When the Large Language Model Meets Programming-The Rise of Code Intelligence. arXiv:2401.14196 [cs.SE] doi:10.48550\/arXiv.2401.14196 10.48550\/arXiv.2401.14196","DOI":"10.48550\/arXiv.2401.14196"},{"key":"e_1_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/MLCAD65511.2025.11189055"},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","unstructured":"Hanxian Huang Zhenghan Lin Zixuan Wang Xin Chen Ke Ding and Jishen Zhao. 2024. Towards llm-powered verilog rtl assistant: Self-verification and self-correction. arXiv:2406.00115 [cs.PL] doi:10.48550\/arXiv.2406.00115 10.48550\/arXiv.2406.00115","DOI":"10.48550\/arXiv.2406.00115"},{"key":"e_1_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1201\/b19569"},{"key":"e_1_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2305.06161"},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2311.00176"},{"key":"e_1_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD57390.2023.10323812"},{"key":"e_1_2_1_24_1","doi-asserted-by":"publisher","unstructured":"Mingjie Liu Yun-Da Tsai Wenfei Zhou and Haoxing Ren. 2025. Craftrtl: High-quality synthetic data generation for verilog code models with correct-by-construction non-textual representations and targeted code repair. arXiv:2409.12993 [cs.AR] doi:10.48550\/arXiv.2409.12993 10.48550\/arXiv.2409.12993","DOI":"10.48550\/arXiv.2409.12993"},{"key":"e_1_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2024.3483089"},{"key":"e_1_2_1_26_1","volume-title":"The Thirteenth International Conference on Learning Representations (ICLR). https:\/\/2.zoppoz.workers.dev:443\/https\/openreview.net\/forum?id=2hcfoCHKoB","author":"Liu Yi","year":"2025","unstructured":"Yi Liu, Changran Xu, Yunhao Zhou, Zeju Li, and Qiang Xu. 2025. Deeprtl: Bridging verilog understanding and generation with a unified representation model. In The Thirteenth International Conference on Learning Representations (ICLR). https:\/\/2.zoppoz.workers.dev:443\/https\/openreview.net\/forum?id=2hcfoCHKoB"},{"key":"e_1_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASP-DAC58780.2024.10473904"},{"key":"e_1_2_1_28_1","unstructured":"Meta AI. 2024. meta-llama\/CodeLlama-70b-Instruct-hf. https:\/\/2.zoppoz.workers.dev:443\/https\/huggingface.co\/meta-llama\/CodeLlama-70b-Instruct-hf"},{"key":"e_1_2_1_29_1","unstructured":"Meta AI. 2024. meta-llama\/llama-models. https:\/\/2.zoppoz.workers.dev:443\/https\/github.com\/meta-llama\/llama-models"},{"key":"e_1_2_1_30_1","unstructured":"Mistral AI. 2024. Au Large. https:\/\/2.zoppoz.workers.dev:443\/https\/mistral.ai\/news\/mistral-large\/"},{"key":"e_1_2_1_31_1","unstructured":"Mistral AI. 2024. Mistral-7B-Instruct-v0.3. https:\/\/2.zoppoz.workers.dev:443\/https\/www.modelscope.cn\/models\/LLM-Research\/Mistral-7B-Instruct-v0.3"},{"key":"e_1_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2015.2513673"},{"key":"e_1_2_1_33_1","doi-asserted-by":"publisher","unstructured":"Erik Nijkamp Bo Pang Hiroaki Hayashi Lifu Tu Huan Wang Yingbo Zhou Silvio Savarese and Caiming Xiong. 2022. CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis. arXiv:2203.13474 [cs.LG] doi:10.48550\/arXiv.2203.13474 10.48550\/arXiv.2203.13474","DOI":"10.48550\/arXiv.2203.13474"},{"key":"e_1_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3718088"},{"key":"e_1_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3733237"},{"key":"e_1_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2308.12950"},{"key":"e_1_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00034-011-9332-7"},{"key":"e_1_2_1_38_1","doi-asserted-by":"publisher","unstructured":"Alexander Shypula Aman Madaan Yimeng Zeng Uri Alon Jacob Gardner Milad Hashemi Graham Neubig Parthasarathy Ranganathan Osbert Bastani and Amir Yazdanbakhsh. 2024. Learning Performance-Improving Code Edits. arXiv:2302.07867 [cs.SE] doi:10.48550\/arXiv.2302.07867 10.48550\/arXiv.2302.07867","DOI":"10.48550\/arXiv.2302.07867"},{"key":"e_1_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.11613\/BM.2008.015"},{"key":"e_1_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/1370750.1370761"},{"key":"e_1_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-16214-0_42"},{"key":"e_1_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.23919\/DATE56975.2023.10137086"},{"key":"e_1_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3643681"},{"key":"e_1_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2311.04887"},{"key":"e_1_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3649329.3657353"},{"key":"e_1_2_1_46_1","doi-asserted-by":"publisher","unstructured":"Ning Wang Bingkun Yao Jie Zhou Yuchen Hu Xi Wang Nan Guan and Zhe Jiang. 2025. Insights from verification: Training a verilog generation LLM with reinforcement learning with testbench feedback. arXiv:2504.15804 [cs.AR] doi:10.48550\/arXiv.2504.15804 10.48550\/arXiv.2504.15804","DOI":"10.48550\/arXiv.2504.15804"},{"key":"e_1_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.5555\/513581.513584"},{"key":"e_1_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.infsof.2022.107043"},{"key":"e_1_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3800680"},{"key":"e_1_2_1_50_1","doi-asserted-by":"publisher","unstructured":"An Yang Anfeng Li Baosong Yang Beichen Zhang Binyuan Hui Bo Zheng Bowen Yu et al. 2025. Qwen3 technical report. arXiv:2505.09388 [cs.CL] doi:10.48550\/arXiv.2505.09388 10.48550\/arXiv.2505.09388","DOI":"10.48550\/arXiv.2505.09388"},{"key":"e_1_2_1_51_1","volume-title":"The Thirteenth International Conference on Learning Representations (ICLR). https:\/\/2.zoppoz.workers.dev:443\/https\/openreview.net\/forum?id=riTiq3i21b","author":"Yang John","year":"2025","unstructured":"John Yang, Carlos E. Jimenez, Alex L. Zhang, Kilian Lieret, Joyce Yang, Xindi Wu, Ori Press, Niklas Muennighoff, Gabriel Synnaeve, Karthik R. Narasimhan, Diyi Yang, Sida I. Wang, and Ofir Press. 2025. SWE-bench Multimodal: Do AI Systems Generalize to Visual Software Domains?. In The Thirteenth International Conference on Learning Representations (ICLR). https:\/\/2.zoppoz.workers.dev:443\/https\/openreview.net\/forum?id=riTiq3i21b"},{"key":"e_1_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.23919\/DATE64628.2025.10993072"},{"key":"e_1_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/3735638"},{"key":"e_1_2_1_54_1","volume-title":"Proceedings of the 41st International Conference on Machine Learning","volume":"235","author":"Zehua PEI","year":"2024","unstructured":"PEI Zehua, Huiling Zhen, Mingxuan Yuan, Yu Huang, and Bei Yu. 2024. Betterv: Controlled verilog generation with discriminative guidance. In Proceedings of the 41st International Conference on Machine Learning, Vol. 235. 40145-40153. https:\/\/2.zoppoz.workers.dev:443\/https\/proceedings.mlr.press\/v235\/pei24e.html"},{"key":"e_1_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/JETCAS.2025.3568712"},{"key":"e_1_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSIC64297"},{"key":"e_1_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/LAD62341.2024.10691738"},{"key":"e_1_2_1_58_1","doi-asserted-by":"publisher","unstructured":"Zejun Zhang Yixin Gan Zhenchang Xing Tian Zhang Yi Li Xiwei Xu Qinghua Lu and Liming Zhu. 2026. Still Manual? Automated Linter Configuration via DSL-Based LLM Compilation of Coding Standards. arXiv:2602.07783 [cs.SE] doi:10.48550\/arXiv.2602.07783 10.48550\/arXiv.2602.07783","DOI":"10.48550\/arXiv.2602.07783"},{"key":"e_1_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1145\/3643776"}],"container-title":["Proceedings of the ACM on Software Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/dl.acm.org\/doi\/pdf\/10.1145\/3797073","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T17:51:16Z","timestamp":1782841876000},"score":1,"resource":{"primary":{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/dl.acm.org\/doi\/10.1145\/3797073"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,30]]},"references-count":59,"journal-issue":{"issue":"FSE","published-print":{"date-parts":[[2026,6,30]]}},"alternative-id":["10.1145\/3797073"],"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1145\/3797073","relation":{},"ISSN":["2994-970X"],"issn-type":[{"value":"2994-970X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,30]]}}}