{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T05:09:01Z","timestamp":1784351341200,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":65,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,9,11]],"date-time":"2024-09-11T00:00:00Z","timestamp":1726012800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National Science and Technology Major Project","award":["2021ZD0112903"],"award-info":[{"award-number":["2021ZD0112903"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,9,11]]},"DOI":"10.1145\/3650212.3652135","type":"proceedings-article","created":{"date-parts":[[2024,9,11]],"date-time":"2024-09-11T11:44:25Z","timestamp":1726055065000},"page":"376-388","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["DiaVio: LLM-Empowered Diagnosis of Safety Violations in ADS Simulation Testing"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-1634-9721","authenticated-orcid":false,"given":"You","family":"Lu","sequence":"first","affiliation":[{"name":"Fudan University, shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-1262-0971","authenticated-orcid":false,"given":"Yifan","family":"Tian","sequence":"additional","affiliation":[{"name":"Fudan University, shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-2292-2627","authenticated-orcid":false,"given":"Yuyang","family":"Bi","sequence":"additional","affiliation":[{"name":"Fudan University, shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7238-7492","authenticated-orcid":false,"given":"Bihuan","family":"Chen","sequence":"additional","affiliation":[{"name":"Fudan University, shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3376-2581","authenticated-orcid":false,"given":"Xin","family":"Peng","sequence":"additional","affiliation":[{"name":"Fudan University, shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,9,11]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3180155.3180160"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3238147.3238192"},{"key":"e_1_3_2_1_3_1","unstructured":"National Highway Traffic Safety Administration. 2016. CIREN (2004-2015) search.. https:\/\/crashviewer.nhtsa.dot.gov\/LegacyCIREN\/Search"},{"key":"e_1_3_2_1_4_1","unstructured":"National Highway Traffic Safety Administration. 2016. NHTSA Crash Viewer.. https:\/\/www.nhtsa.gov\/"},{"key":"e_1_3_2_1_5_1","unstructured":"National Highway Traffic Safety Administration. 2016. NMVCCS (2005-2007) search.. https:\/\/crashviewer.nhtsa.dot.gov\/LegacyNMVCCS\/Search"},{"key":"e_1_3_2_1_6_1","unstructured":"ASAM. 2021. ASAM OpenSCENARIO: User Guide.. https:\/\/www.asam.net\/index.php?eID=dumpFile&t=f&f=4092&token=d3b6a55e911b22179e3c0895fe2caae8f5492467"},{"key":"e_1_3_2_1_7_1","unstructured":"Knowledge Engineering Group (KEG) & Data Mining at Tsinghua University. 2023. ChatGLM3-6B. https:\/\/huggingface.co\/THUDM\/chatglm2-6b"},{"key":"e_1_3_2_1_8_1","unstructured":"Daniel Atherton. 2022. Incident 434: Sudden Braking by Tesla Allegedly on Self-Driving Mode Caused Multi-Car Pileup in Tunnel. In AI Incident Database Khoa Lam (Ed.). Responsible AI Collaborative. https:\/\/incidentdatabase.ai\/cite\/434\/"},{"key":"e_1_3_2_1_9_1","volume-title":"Apollo: An open autonomous driving platform. https:\/\/github.com\/ApolloAuto\/apollo","year":"2022","unstructured":"Baidu. 2022. Apollo: An open autonomous driving platform. https:\/\/github.com\/ApolloAuto\/apollo"},{"key":"e_1_3_2_1_10_1","volume-title":"Proceedings of the Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and\/or Summarization. 65\u201372","author":"Banerjee Satanjeev","year":"2005","unstructured":"Satanjeev Banerjee and Alon Lavie. 2005. METEOR: An automatic metric for MT evaluation with improved correlation with human judgments. In Proceedings of the Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and\/or Summarization. 65\u201372."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/2970276.2970311"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.aap.2019.105267"},{"key":"e_1_3_2_1_13_1","unstructured":"CARLA. 2023. CARLA Agents. https:\/\/carla.readthedocs.io\/en\/0.9.12\/adv_agents\/"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3091477"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3597926.3598072"},{"key":"e_1_3_2_1_16_1","unstructured":"Alibaba Cloud. 2023. Qwen-14B-Chat. https:\/\/huggingface.co\/Qwen\/Qwen-14B-Chat"},{"key":"e_1_3_2_1_17_1","unstructured":"Alibaba Cloud. 2023. Qwen-7B-Chat. https:\/\/huggingface.co\/Qwen\/Qwen-7B-Chat"},{"key":"e_1_3_2_1_18_1","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 4171\u20134186","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. Bert: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 4171\u20134186."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3259322"},{"key":"e_1_3_2_1_20_1","volume-title":"Proceedings of the 1st Annual Conference on Robot Learning. 1\u201316","author":"Dosovitskiy Alexey","year":"2017","unstructured":"Alexey Dosovitskiy, German Ros, Felipe Codevilla, Antonio Lopez, and Vladlen Koltun. 2017. CARLA: An Open Urban Driving Simulator. In Proceedings of the 1st Annual Conference on Robot Learning. 1\u201316."},{"key":"e_1_3_2_1_21_1","volume-title":"Proceedings of the 40th ACM SIGPLAN Conference on Programming Language Design and Implementation. 63\u201378","author":"Fremont Daniel J.","unstructured":"Daniel J. Fremont, Tommaso Dreossi, Shromona Ghosh, Xiangyu Yue, Alberto L. Sangiovanni-Vincentelli, and Sanjit A. Seshia. 2019. Scenic: A Language for Scenario Specification and Scene Generation. In Proceedings of the 40th ACM SIGPLAN Conference on Programming Language Design and Implementation. 63\u201378."},{"key":"e_1_3_2_1_22_1","volume-title":"Proceedings of the 34th IEEE\/ACM International Conference on Automated Software Engineering. 26\u201337","author":"Gladisch Christoph","year":"2020","unstructured":"Christoph Gladisch, Thomas Heinz, Christian Heinzemann, Jens Oehlerking, Anne von Vietinghoff, and Tim Pfitzer. 2020. Experience Paper: Search-Based Testing in Automated Driving Control Applications. In Proceedings of the 34th IEEE\/ACM International Conference on Automated Software Engineering. 26\u201337."},{"key":"e_1_3_2_1_23_1","volume-title":"Proceedings of the IEEE 13th International Conference on Software Testing, Validation and Verification. 85\u201395","author":"Haq Fitash Ul","unstructured":"Fitash Ul Haq, Donghwan Shin, Shiva Nejati, and Lionel C. Briand. 2020. Comparing Offline and Online Testing of Deep Neural Networks: An Autonomous Car Case Study. In Proceedings of the IEEE 13th International Conference on Software Testing, Validation and Verification. 85\u201395."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3597926.3598069"},{"key":"e_1_3_2_1_25_1","volume-title":"Proceedings of the 10th International Conference on Learning Representations.","author":"Hu Edward J","year":"2022","unstructured":"Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2022. Lora: Low-rank adaptation of large language models. In Proceedings of the 10th International Conference on Learning Representations."},{"key":"e_1_3_2_1_26_1","unstructured":"Yuqi Huai. 2023. SORA-SVL. https:\/\/www.ics.uci.edu\/~yhuai\/SORA-SVL\/"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2023.3309610"},{"key":"e_1_3_2_1_28_1","volume-title":"Proceedings of the 2023 IEEE\/ACM 45th International Conference on Software Engineering. 2591\u20132603","author":"Huai Yuqi","year":"2023","unstructured":"Yuqi Huai, Yuntianyi Chen, Sumaya Almanee, Tuan Ngo, Xiang Liao, Ziwen Wan, Qi Alfred Chen, and Joshua Garcia. 2023. Doppelg\u00e4nger Test Generation for Revealing Bugs in Autonomous Driving Software. In Proceedings of the 2023 IEEE\/ACM 45th International Conference on Software Engineering. 2591\u20132603."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC48978.2021.9564428"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.tra.2016.09.010"},{"key":"e_1_3_2_1_31_1","volume-title":"Proceedings of the 1st Workshop on Evaluating NLG Evaluation. 28\u201337","author":"Kane Hassan","year":"2020","unstructured":"Hassan Kane, Muhammed Yusuf Kocyigit, Ali Abdalla, Pelkins Ajanoh, and Mohamed Coulibali. 2020. NUBIA: NeUral based interchangeability assessor for text generation. In Proceedings of the 1st Workshop on Evaluating NLG Evaluation. 28\u201337."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/MetroCAD51599.2021.00018"},{"key":"e_1_3_2_1_33_1","volume-title":"Driving away from Support Crew","author":"Khemka Srishti","unstructured":"Srishti Khemka. 2021. Incident 347: Waymo Self-Driving Taxi Behaved Unexpectedly, Driving away from Support Crew. In AI Incident Database, Khoa Lam (Ed.). Responsible AI Collaborative. https:\/\/incidentdatabase.ai\/cite\/347\/"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3548606.3560558"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3597926.3598100"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISSRE5003.2020.00012"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2016.2608003"},{"key":"e_1_3_2_1_38_1","volume-title":"Proceedings of the Workshop on Text Summarization Branches Out. 74\u201381","author":"Lin Chin-Yew","year":"2004","unstructured":"Chin-Yew Lin. 2004. Rouge: A package for automatic evaluation of summaries. In Proceedings of the Workshop on Text Summarization Branches Out. 74\u201381."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.3115\/1220355.1220427"},{"key":"e_1_3_2_1_40_1","volume-title":"Proceedings of the 7th International Conference on Learning Representations.","author":"Loshchilov Ilya","year":"2019","unstructured":"Ilya Loshchilov and Frank Hutter. 2019. Decoupled weight decay regularization. In Proceedings of the 7th International Conference on Learning Representations."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3540250.3549111"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE-Companion58688.2023.00086"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2022.3150788"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASE51524.2021.9678883"},{"key":"e_1_3_2_1_45_1","unstructured":"Sean McGregor. 2018. Incident 4: Uber AV Killed Pedestrian in Arizona. In AI Incident Database Sean McGregor (Ed.). Responsible AI Collaborative. https:\/\/incidentdatabase.ai\/cite\/4"},{"key":"e_1_3_2_1_46_1","unstructured":"Meta. 2023. Llama-2-13b-chat-hf. https:\/\/huggingface.co\/meta-llama\/Llama-2-13b-chat-hf"},{"key":"e_1_3_2_1_47_1","unstructured":"Meta. 2023. Llama-2-70b-chat-hf. https:\/\/huggingface.co\/meta-llama\/Llama-2-70b-chat-hf"},{"key":"e_1_3_2_1_48_1","unstructured":"Meta. 2023. Llama-2-7b-chat-hf. https:\/\/huggingface.co\/meta-llama\/Llama-2-7b-chat-hf"},{"key":"e_1_3_2_1_49_1","unstructured":"Wassim G Najm Raja Ranganathan Gowrishankar Srinivasan John D Smith Samuel Toma Elizabeth D Swanson and August Burgett. 2013. Description of light-vehicle pre-crash scenarios for safety applications based on vehicle-to-vehicle communications. United States. Department of Transportation. National Highway Traffic Safety."},{"key":"e_1_3_2_1_50_1","unstructured":"Wassim G Najm John D Smith and Mikio Yanagisawa. 2007. Pre-crash scenario typology for crash avoidance research. United States. National Highway Traffic Safety Administration."},{"key":"e_1_3_2_1_51_1","unstructured":"OpenAI. 2022. Introducing ChatGPT. https:\/\/openai.com\/blog\/chatgpt"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2016.2578706"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2019.8814107"},{"key":"e_1_3_2_1_54_1","unstructured":"Sebastian Raschka. 2023. Finetuning LLMs with LoRA and QLoRA: Insights from Hundreds of Experiments. https:\/\/lightning.ai\/pages\/community\/lora-insights\/"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.704"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/3551349.3556897"},{"key":"e_1_3_2_1_57_1","unstructured":"Baichuan Intelligent Technology. 2023. Baichuan 2. https:\/\/huggingface.co\/baichuan-inc\/Baichuan2-7B-Chat"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/3540250.3549100"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1145\/3551349.3560430"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1145\/3520312.3534862"},{"key":"e_1_3_2_1_61_1","volume-title":"Proceedings of the 8th International Conference on Learning Representations.","author":"Zhang Tianyi","year":"2020","unstructured":"Tianyi Zhang, Varsha Kishore, Felix Wu, Kilian Q Weinberger, and Yoav Artzi. 2020. Bertscore: Evaluating text generation with bert. In Proceedings of the 8th International Conference on Learning Representations."},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2022.3170122"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1145\/3597926.3598108"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2022.3195640"},{"key":"e_1_3_2_1_65_1","volume-title":"Yang Liu, and Baishakhi Ray.","author":"Zhong Ziyuan","year":"2021","unstructured":"Ziyuan Zhong, Yun Tang, Yuan Zhou, Vania de Oliveira Neves, Yang Liu, and Baishakhi Ray. 2021. A survey on scenario-based testing for automated driving systems in high-fidelity simulation. arXiv preprint arXiv:2112.00964."}],"event":{"name":"ISSTA '24: 33rd ACM SIGSOFT International Symposium on Software Testing and Analysis","location":"Vienna Austria","acronym":"ISSTA '24","sponsor":["SIGSOFT ACM Special Interest Group on Software Engineering","AITO"]},"container-title":["Proceedings of the 33rd ACM SIGSOFT International Symposium on Software Testing and Analysis"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3650212.3652135","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3650212.3652135","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T22:50:06Z","timestamp":1750287006000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3650212.3652135"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,11]]},"references-count":65,"alternative-id":["10.1145\/3650212.3652135","10.1145\/3650212"],"URL":"https:\/\/doi.org\/10.1145\/3650212.3652135","relation":{},"subject":[],"published":{"date-parts":[[2024,9,11]]},"assertion":[{"value":"2024-09-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}