{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T15:52:57Z","timestamp":1781020377782,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":54,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62402038"],"award-info":[{"award-number":["62402038"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62192730"],"award-info":[{"award-number":["62192730"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62192735"],"award-info":[{"award-number":["62192735"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U21B2015"],"award-info":[{"award-number":["U21B2015"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,6,23]]},"DOI":"10.1145\/3696630.3728560","type":"proceedings-article","created":{"date-parts":[[2025,7,28]],"date-time":"2025-07-28T19:09:27Z","timestamp":1753729767000},"page":"366-377","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Evaluating Large Language Models for Requirements Question Answering in Industrial Aerospace Software"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-6122-1549","authenticated-orcid":false,"given":"Longxing","family":"Yang","sequence":"first","affiliation":[{"name":"Beijing Institute of Control Engineering, Beijing, 86, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6223-5217","authenticated-orcid":false,"given":"Yixing","family":"Luo","sequence":"additional","affiliation":[{"name":"Beijing Institute of Control Engineering, Beijing, 86, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1586-8542","authenticated-orcid":false,"given":"Hao","family":"Gao","sequence":"additional","affiliation":[{"name":"Beijing Institute of Control Engineering, Beijing, 86, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-9888-6904","authenticated-orcid":false,"given":"Yingshuang","family":"Fan","sequence":"additional","affiliation":[{"name":"Beijing Institute of Control Engineering, Beijing, 86, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-3102-0635","authenticated-orcid":false,"given":"Jingru","family":"Zhang","sequence":"additional","affiliation":[{"name":"Beijing Institute of Control Engineering, Beijing, 86, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-8805-665X","authenticated-orcid":false,"given":"Xiaofeng","family":"Li","sequence":"additional","affiliation":[{"name":"Beijing Institute of Control Engineering, Beijing, 86, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-8327-5154","authenticated-orcid":false,"given":"Xiaogang","family":"Dong","sequence":"additional","affiliation":[{"name":"Beijing Institute of Control Engineering, Beijing, 86, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7218-4839","authenticated-orcid":false,"given":"Bin","family":"Gu","sequence":"additional","affiliation":[{"name":"Beijing Institute of Control Engineering, Beijing, 86, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1087-226X","authenticated-orcid":false,"given":"Zhi","family":"Jin","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, 86, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6844-1246","authenticated-orcid":false,"given":"Mengfei","family":"Yang","sequence":"additional","affiliation":[{"name":"China Academy of Space Technology, Beijing, 86, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,7,28]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"SemDeDup: Data-efficient learning at web-scale through semantic deduplication. arXiv preprint arXiv:2303.09540","author":"Abbas Amro","year":"2023","unstructured":"Amro Abbas, Kushal Tirumala, D\u00e1niel Simig, Surya Ganguli, and Ari S Morcos. 2023. SemDeDup: Data-efficient learning at web-scale through semantic deduplication. arXiv preprint arXiv:2303.09540 (2023)."},{"key":"e_1_3_2_1_2_1","volume-title":"Proceedings of the 30th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering. 1682\u20131686","author":"Abualhaija Sallam","year":"2022","unstructured":"Sallam Abualhaija, Chetan Arora, and Lionel C Briand. 2022. COREQQA: a COmpliance REQuirements understanding using question answering tool. In Proceedings of the 30th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering. 1682\u20131686."},{"key":"e_1_3_2_1_3_1","volume-title":"Automated question answering for improved understanding of compliance requirements: A multi-document study. In 2022 IEEE 30th international requirements engineering conference (RE)","author":"Abualhaija Sallam","unstructured":"Sallam Abualhaija, Chetan Arora, Amin Sleimi, and Lionel C Briand. 2022. Automated question answering for improved understanding of compliance requirements: A multi-document study. In 2022 IEEE 30th international requirements engineering conference (RE). IEEE, 39\u201350."},{"key":"e_1_3_2_1_4_1","volume-title":"Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al.","author":"Achiam Josh","year":"2023","unstructured":"Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al. 2023. Gpt-4 technical report. arXiv preprint arXiv:2303.08774 (2023)."},{"key":"e_1_3_2_1_5_1","volume-title":"Yevhen Mohylevskyy, Neel Sundaresan, and Michele Tufano.","author":"Agarwal Anisha","year":"2024","unstructured":"Anisha Agarwal, Aaron Chan, Shubham Chandel, Jinu Jang, Shaun Miller, Roshanak Zilouchian Moghaddam, Yevhen Mohylevskyy, Neel Sundaresan, and Michele Tufano. 2024. Copilot Evaluation Harness: Evaluating LLM-Guided Software Programming. arXiv preprint arXiv:2402.14261 (2024)."},{"key":"e_1_3_2_1_6_1","unstructured":"Janice Ahn Rishu Verma Renze Lou Di Liu Rui Zhang and Wenpeng Yin. 2024. Large Language Models for Mathematical Reasoning: Progresses and Challenges. arXiv:2402.00157 [cs.CL]"},{"key":"e_1_3_2_1_7_1","volume-title":"Generative AI for Effective Software Development","author":"Arora Chetan","unstructured":"Chetan Arora, John Grundy, and Mohamed Abdelrazek. 2024. Advancing requirements engineering through generative ai: Assessing the role of llms. In Generative AI for Effective Software Development. Springer, 129\u2013148."},{"key":"e_1_3_2_1_8_1","volume-title":"2015 IEEE 23rd International Requirements Engineering Conference (RE). IEEE, 6\u201315","author":"Arora Chetan","year":"2015","unstructured":"Chetan Arora, Mehrdad Sabetzadeh, Arda Goknil, Lionel C Briand, and Frank Zimmer. 2015. Change impact analysis for natural language requirements: An NLP approach. In 2015 IEEE 23rd International Requirements Engineering Conference (RE). IEEE, 6\u201315."},{"key":"e_1_3_2_1_9_1","volume-title":"Proceedings of the 2015 10th Joint Meeting on Foundations of Software Engineering. 962\u2013965","author":"Arora Chetan","year":"2015","unstructured":"Chetan Arora, Mehrdad Sabetzadeh, Arda Goknil, Lionel C Briand, and Frank Zimmer. 2015. NARCIA: an automated tool for change impact analysis in natural language requirements. In Proceedings of the 2015 10th Joint Meeting on Foundations of Software Engineering. 962\u2013965."},{"key":"e_1_3_2_1_10_1","unstructured":"Simon Arvidsson and Johan Axell. 2023. Prompt engineering guidelines for LLMs in Requirements Engineering. (2023)."},{"key":"e_1_3_2_1_11_1","volume-title":"Proceedings. Compression and Complexity of SEQUENCES 1997 (Cat. No.97TB100171)","author":"Broder A.Z.","year":"1997","unstructured":"A.Z. Broder. 1997. On the resemblance and containment of documents. In Proceedings. Compression and Complexity of SEQUENCES 1997 (Cat. No.97TB100171). 21\u201329."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"crossref","first-page":"287","DOI":"10.1016\/j.procir.2014.07.127","article-title":"An aerospace requirements setting model to improve system design","volume":"22","author":"Centrich X Tomas","year":"2014","unstructured":"X Tomas Centrich, Essam Shehab, Piotr Sydor, Tim Mackley, Philip John, and A Harrison. 2014. An aerospace requirements setting model to improve system design. Procedia CIRP 22 (2014), 287\u2013292.","journal-title":"Procedia CIRP"},{"key":"e_1_3_2_1_13_1","unstructured":"Yezeng Chen Zui Chen and Yi Zhou. 2024. Brain-Inspired Two-Stage Approach: Enhancing Mathematical Reasoning by Imitating Human Thought Processes. arXiv:2403.00800 [cs.CL]"},{"key":"e_1_3_2_1_14_1","unstructured":"Karl Cobbe Vineet Kosaraju Mohammad Bavarian Mark Chen Heewoo Jun Lukasz Kaiser Matthias Plappert Jerry Tworek Jacob Hilton Reiichiro Nakano Christopher Hesse and John Schulman. 2021. Training Verifiers to Solve Math Word Problems. arXiv:2110.14168 [cs.LG]"},{"key":"e_1_3_2_1_15_1","volume-title":"International Conference on Learning Representations.","author":"Dai Zhuyun","year":"2023","unstructured":"Zhuyun Dai, Vincent Y Zhao, Ji Ma, Yi Luan, Jianmo Ni, Jing Lu, Anton Bakalov, Kelvin Guu, Keith Hall, and Ming-Wei Chang. 2023. Promptagator: Few-shot Dense Retrieval From 8 Examples. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_16_1","volume-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In North American","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 North American Chapter of the Association for Computational Linguistics."},{"key":"e_1_3_2_1_17_1","volume-title":"2023 IEEE\/ACM 45th International Conference on Software Engineering (ICSE). IEEE, 1277\u20131289","author":"Ezzini Saad","year":"2023","unstructured":"Saad Ezzini, Sallam Abualhaija, Chetan Arora, and Mehrdad Sabetzadeh. 2023. Ai-based question answering assistance for analyzing natural-language requirements. In 2023 IEEE\/ACM 45th International Conference on Software Engineering (ICSE). IEEE, 1277\u20131289."},{"key":"e_1_3_2_1_18_1","volume-title":"2023 IEEE 31st International Requirements Engineering Conference (RE). IEEE, 335\u2013340","author":"Fantechi Alessandro","year":"2023","unstructured":"Alessandro Fantechi, Stefania Gnesi, Lucia Passaro, and Laura Semini. 2023. Inconsistency detection in natural language requirements using chatgpt: a preliminary evaluation. In 2023 IEEE 31st International Requirements Engineering Conference (RE). IEEE, 335\u2013340."},{"key":"e_1_3_2_1_19_1","unstructured":"Dan Hendrycks Collin Burns Saurav Kadavath Akul Arora Steven Basart Eric Tang Dawn Song and Jacob Steinhardt. 2021. Measuring Mathematical Problem Solving With the MATH Dataset. arXiv:2103.03874 [cs.LG]"},{"key":"e_1_3_2_1_20_1","unstructured":"Lei Huang Weijiang Yu Weitao Ma Weihong Zhong Zhangyin Feng Haotian Wang Qianglong Chen Weihua Peng Xiaocheng Feng Bing Qin et al. 2023. A survey on hallucination in large language models: Principles taxonomy challenges and open questions. arXiv preprint arXiv:2311.05232 (2023)."},{"key":"e_1_3_2_1_21_1","volume-title":"2017 IEEE 25th International Requirements Engineering Conference (RE). IEEE.","author":"Kanchev Georgi M","year":"2017","unstructured":"Georgi M Kanchev, Pradeep K Murukannaiah, Amit K Chopra, and Pete Sawyer. 2017. Canary: an interactive and query-based approach to extract requirements from online forums. In 2017 IEEE 25th International Requirements Engineering Conference (RE). IEEE."},{"key":"e_1_3_2_1_22_1","volume-title":"Using LLMs in Software Requirements Specifications: An Empirical Evaluation. arXiv preprint arXiv:2404.17842","author":"Krishna Madhava","year":"2024","unstructured":"Madhava Krishna, Bhagesh Gaur, Arsh Verma, and Pankaj Jalote. 2024. Using LLMs in Software Requirements Specifications: An Empirical Evaluation. arXiv preprint arXiv:2404.17842 (2024)."},{"key":"e_1_3_2_1_23_1","volume-title":"A technique for the measurement of attitudes. Archives of Psychology","author":"Likert Rensis","year":"1932","unstructured":"Rensis Likert. 1932. A technique for the measurement of attitudes. Archives of Psychology (1932)."},{"key":"e_1_3_2_1_24_1","volume-title":"ROUGE: A Package for Automatic Evaluation of Summaries. In Text Summarization Branches Out","author":"Lin Chin-Yew","year":"2004","unstructured":"Chin-Yew Lin. 2004. ROUGE: A Package for Automatic Evaluation of Summaries. In Text Summarization Branches Out. Association for Computational Linguistics, Barcelona, Spain."},{"key":"e_1_3_2_1_25_1","volume-title":"2017 32nd IEEE\/ACM International Conference on Automated Software Engineering (ASE). IEEE.","author":"Lin Jinfeng","year":"2017","unstructured":"Jinfeng Lin, Yalin Liu, Jin Guo, Jane Cleland-Huang, William Goss, Wenchuang Liu, Sugandha Lohar, Natawut Monaikul, and Alexander Rasin. 2017. Tiqi: A natural language interface for querying software project data. In 2017 32nd IEEE\/ACM International Conference on Automated Software Engineering (ASE). IEEE."},{"key":"e_1_3_2_1_26_1","volume-title":"Codexglue: A machine learning benchmark dataset for code understanding and generation. arXiv preprint arXiv:2102.04664","author":"Lu Shuai","year":"2021","unstructured":"Shuai Lu, Daya Guo, Shuo Ren, Junjie Huang, Alexey Svyatkovskiy, Ambrosio Blanco, Colin Clement, Dawn Drain, Daxin Jiang, Duyu Tang, et al. 2021. Codexglue: A machine learning benchmark dataset for code understanding and generation. arXiv preprint arXiv:2102.04664 (2021)."},{"key":"e_1_3_2_1_27_1","volume-title":"Improving requirements completeness: Automated assistance through large language models. Requirements Engineering","author":"Luitel Dipeeka","year":"2024","unstructured":"Dipeeka Luitel, Shabnam Hassani, and Mehrdad Sabetzadeh. 2024. Improving requirements completeness: Automated assistance through large language models. Requirements Engineering (2024)."},{"key":"e_1_3_2_1_28_1","volume-title":"Proceedings of the 37th IEEE\/ACM International Conference on Automated Software Engineering. 1\u201313","author":"Luo Xianchang","year":"2022","unstructured":"Xianchang Luo, Yinxing Xue, Zhenchang Xing, and Jiamou Sun. 2022. Prcbert: Prompt learning for requirement classification using bert-based pretrained language models. In Proceedings of the 37th IEEE\/ACM International Conference on Automated Software Engineering. 1\u201313."},{"key":"e_1_3_2_1_29_1","volume-title":"International Conference on Human-Computer Interaction.","author":"Lutze Rainer","year":"2024","unstructured":"Rainer Lutze and Klemens Waldh\u00f6r. 2024. Generating Specifications from Requirements Documents for Smart Devices Using Large Language Models (LLMs). In International Conference on Human-Computer Interaction."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"crossref","unstructured":"John MacFarlane. 2006\u2013. Pandoc. Accessed: 2024-08-22.","DOI":"10.1016\/j.yadr.2006.07.002"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"crossref","first-page":"537","DOI":"10.1007\/s10270-012-0237-0","article-title":"A visual language for modeling and executing traceability queries","volume":"12","author":"M\u00e4der Patrick","year":"2013","unstructured":"Patrick M\u00e4der and Jane Cleland-Huang. 2013. A visual language for modeling and executing traceability queries. Software & Systems Modeling 12 (2013), 537\u2013553.","journal-title":"Software & Systems Modeling"},{"key":"e_1_3_2_1_32_1","unstructured":"Gary Musgrave Axel Larsen and Tommaso Sgobba (Eds.). 2009. Safety Design for Space Systems. Elsevier Oxford."},{"key":"e_1_3_2_1_33_1","volume-title":"Juha Savolainen, and Jing-Ru C Cheng.","author":"Niu Nan","year":"2018","unstructured":"Nan Niu, Wentao Wang, Arushi Gupta, Mona Assarandarban, Li Da Xu, Juha Savolainen, and Jing-Ru C Cheng. 2018. Requirements socio-technical graphs for managing practitioners' traceability questions. IEEE Transactions on Computational Social Systems (2018)."},{"key":"e_1_3_2_1_34_1","volume-title":"Structuring Natural Language Requirements with Large Language Models. In 2024 IEEE 32nd International Requirements Engineering Conference Workshops (REW). IEEE, 68\u201371","author":"Norheim Johannes J","year":"2024","unstructured":"Johannes J Norheim and Eric Rebentisch. 2024. Structuring Natural Language Requirements with Large Language Models. In 2024 IEEE 32nd International Requirements Engineering Conference Workshops (REW). IEEE, 68\u201371."},{"key":"e_1_3_2_1_35_1","volume-title":"Exploring the limits of transfer learning with a unified text-to-text transformer. Journal of machine learning research","author":"Raffel Colin","year":"2020","unstructured":"Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J Liu. 2020. Exploring the limits of transfer learning with a unified text-to-text transformer. Journal of machine learning research (2020)."},{"key":"e_1_3_2_1_36_1","volume-title":"Automated User Story Generation with Test Case Specification Using Large Language Model. arXiv preprint arXiv:2404.01558","author":"Rahman Tajmilur","year":"2024","unstructured":"Tajmilur Rahman and Yuecai Zhu. 2024. Automated User Story Generation with Test Case Specification Using Large Language Model. arXiv preprint arXiv:2404.01558 (2024)."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-srw.49"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1002\/WIDM.1482"},{"key":"e_1_3_2_1_39_1","volume-title":"A query system for extracting requirements-related information from legal texts. In 2019 IEEE 27th international requirements engineering conference (RE)","author":"Sleimi Amin","unstructured":"Amin Sleimi, Marcello Ceci, Nicolas Sannier, Mehrdad Sabetzadeh, Lionel Briand, and John Dann. 2019. A query system for extracting requirements-related information from legal texts. In 2019 IEEE 27th international requirements engineering conference (RE). IEEE."},{"key":"e_1_3_2_1_40_1","volume-title":"2020 AIAA\/IEEE 39th Digital Avionics Systems Conference (DASC). IEEE, 1\u20138.","author":"Subarna S","year":"2020","unstructured":"S Subarna, Ankita K Jawale, Akshay S Vidap, Subodh D Sadachar, Shana Fliginger, and Srimannarayana Myla. 2020. Using a model based systems engineering approach for aerospace system requirements management. In 2020 AIAA\/IEEE 39th Digital Avionics Systems Conference (DASC). IEEE, 1\u20138."},{"key":"e_1_3_2_1_41_1","unstructured":"RapidAI Team. 2021. Rapid OCR: OCR Toolbox."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"crossref","first-page":"279","DOI":"10.3390\/aerospace10030279","article-title":"aerobert-classifier: Classification of aerospace requirements using bert","volume":"10","author":"Ray Archana Tikayat","year":"2023","unstructured":"Archana Tikayat Ray, Bjorn F Cole, Olivia J Pinon Fischer, Ryan T White, and Dimitri N Mavris. 2023. aerobert-classifier: Classification of aerospace requirements using bert. Aerospace 10, 3 (2023), 279.","journal-title":"Aerospace"},{"key":"e_1_3_2_1_43_1","volume-title":"Software Engineering for Aerospace: State of the Art. Autonomy requirements engineering for space missions","author":"Vassev Emil","year":"2014","unstructured":"Emil Vassev, Mike Hinchey, Emil Vassev, and Mike Hinchey. 2014. Software Engineering for Aerospace: State of the Art. Autonomy requirements engineering for space missions (2014)."},{"key":"e_1_3_2_1_44_1","volume-title":"CMATH: Can Your Language Model Pass Chinese Elementary School Math Test? arXiv:2306.16636 [cs.CL]","author":"Wei Tianwen","year":"2023","unstructured":"Tianwen Wei, Jian Luan, Wei Liu, Shuang Dong, and Bin Wang. 2023. CMATH: Can Your Language Model Pass Chinese Elementary School Math Test? arXiv:2306.16636 [cs.CL]"},{"key":"e_1_3_2_1_45_1","volume-title":"2021 IEEE Aerospace Conference (50100)","author":"Wein Shira","year":"2021","unstructured":"Shira Wein and Paul Briggs. 2021. A fully automated approach to requirement extraction from design documents. In 2021 IEEE Aerospace Conference (50100). IEEE, 1\u20137."},{"key":"e_1_3_2_1_46_1","unstructured":"Shitao Xiao Zheng Liu Peitian Zhang and Niklas Muennighoff. 2023. C-Pack: Packaged Resources To Advance General Chinese Embedding. arXiv:2309.07597 [cs.CL]"},{"key":"e_1_3_2_1_47_1","unstructured":"Aiyuan Yang Bin Xiao Bingning Wang Borong Zhang Ce Bian Chao Yin Chenxu Lv Da Pan Dian Wang Dong Yan et al. 2023. Baichuan 2: Open large-scale language models. arXiv preprint arXiv:2309.10305 (2023)."},{"key":"e_1_3_2_1_48_1","unstructured":"An Yang Baosong Yang Binyuan Hui Bo Zheng Bowen Yu Chang Zhou Chengpeng Li Chengyuan Li Dayiheng Liu Fei Huang Guanting Dong Haoran Wei Huan Lin Jialong Tang Jialin Wang Jian Yang Jianhong Tu Jianwei Zhang Jianxin Ma Jin Xu Jingren Zhou Jinze Bai Jinzheng He Junyang Lin Kai Dang Kerning Lu Ke-Yang Chen Kexin Yang Mei Li Min Xue Na Ni Pei Zhang Peng Wang Ru Peng Rui Men Ruize Gao Runji Lin Shijie Wang Shuai Bai Sinan Tan Tianhang Zhu Tianhao Li Tianyu Liu Wenbin Ge Xiaodong Deng Xiaohuan Zhou Xingzhang Ren Xinyu Zhang Xipin Wei Xuancheng Ren Yang Fan Yang Yao Yichang Zhang Yunyang Wan Yunfei Chu Zeyu Cui Zhenru Zhang and Zhi-Wei Fan. 2024. Qwen2 Technical Report. ArXiv abs\/2407.10671 (2024)."},{"key":"e_1_3_2_1_49_1","first-page":"1","article-title":"Intelligent program synthesis framework and key scientific problems for embedded software","volume":"42","author":"Yang Mengfei","year":"2022","unstructured":"Mengfei Yang, Bin Gu, Zhenhua Duan, Zhi Jin, Naijun Zhan, Yunwei Dong, Cong Tian, Ge Li, Xiaogang Dong, and Xiaofeng Li. 2022. Intelligent program synthesis framework and key scientific problems for embedded software. Chinese Space Science and Technology 42, 4 (2022), 1\u20137. in Chinese.","journal-title":"Chinese Space Science and Technology"},{"key":"e_1_3_2_1_50_1","unstructured":"Zhen Yang Ming Ding Qingsong Lv Zhihuan Jiang Zehai He Yuyi Guo Jinfeng Bai and Jie Tang. 2023. GPT Can Solve Mathematical Problems Without a Calculator. arXiv:2309.03241 [cs.LG]"},{"key":"e_1_3_2_1_51_1","unstructured":"Team Glm Aohan Zeng Bin Xu Bowen Wang Chenhui Zhang Da Yin Diego Rojas Guanyu Feng Hanlin Zhao Hanyu Lai Hao Yu Hongning Wang Jiadai Sun Jiajie Zhang Jiale Cheng Jiayi Gui Jie Tang Jing Zhang Juanzi Li Lei Zhao Lindong Wu Lucen Zhong Ming yue Liu Minlie Huang Peng Zhang Qinkai Zheng Rui Lu Shuaiqi Duan Shudan Zhang Shulin Cao Shuxun Yang Weng Lam Tam Wenyi Zhao Xiao Liu Xiaoyu Xia Xiaohan Zhang Xiaotao Gu Xin Lv Xinghan Liu Xinyi Liu Xinyue Yang Xixuan Song Xunkai Zhang Yi An Yifan Xu Yilin Niu Yuantao Yang Yueyan Li Yushi Bai Yuxiao Dong Zehan Qi Zhaoyu Wang Zhenyi Yang Zhengxiao Du Zhen-Ping Hou and Zihan Wang. 2024. ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools. ArXiv abs\/2406.12793 (2024)."},{"key":"e_1_3_2_1_52_1","unstructured":"Wayne Xin Zhao Kun Zhou Junyi Li Tianyi Tang Xiaolei Wang Yupeng Hou Yingqian Min Beichen Zhang Junjie Zhang Zican Dong et al. 2023. A survey of large language models. arXiv preprint arXiv:2303.18223 (2023)."},{"key":"e_1_3_2_1_53_1","first-page":"46595","article-title":"Judging llm-as-a-judge with mt-bench and chatbot arena","volume":"36","author":"Zheng Lianmin","year":"2023","unstructured":"Lianmin Zheng, Wei-Lin Chiang, Ying Sheng, Siyuan Zhuang, Zhanghao Wu, Yonghao Zhuang, Zi Lin, Zhuohan Li, Dacheng Li, Eric Xing, et al. 2023. Judging llm-as-a-judge with mt-bench and chatbot arena. Advances in Neural Information Processing Systems 36 (2023), 46595\u201346623.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"crossref","unstructured":"Wanjun Zhong Ruixiang Cui Yiduo Guo Yaobo Liang Shuai Lu Yanlin Wang Amin Saied Weizhu Chen and Nan Duan. 2023. AGIEval: A Human-Centric Benchmark for Evaluating Foundation Models. arXiv:2304.06364 [cs.CL]","DOI":"10.18653\/v1\/2024.findings-naacl.149"}],"event":{"name":"FSE Companion '25: 33rd ACM International Conference on the Foundations of Software Engineering","location":"Clarion Hotel Trondheim Trondheim Norway","acronym":"FSE Companion '25","sponsor":["SIGSOFT ACM Special Interest Group on Software Engineering"]},"container-title":["Proceedings of the 33rd ACM International Conference on the Foundations of Software Engineering"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3696630.3728560","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,28]],"date-time":"2025-07-28T19:13:36Z","timestamp":1753730016000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3696630.3728560"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,23]]},"references-count":54,"alternative-id":["10.1145\/3696630.3728560","10.1145\/3696630"],"URL":"https:\/\/doi.org\/10.1145\/3696630.3728560","relation":{},"subject":[],"published":{"date-parts":[[2025,6,23]]},"assertion":[{"value":"2025-07-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}