{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T20:31:04Z","timestamp":1792787464838,"version":"4.5.0"},"publisher-location":"New York, NY, USA","reference-count":94,"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 Natural Science Foundation of China","award":["62322208, 62232001"],"award-info":[{"award-number":["62322208, 62232001"]}]},{"name":"CCF Young Elite Scientists Sponsorship Program (by CAST)","award":[""],"award-info":[{"award-number":[""]}]},{"name":"JSPS for the KAKENHI","award":["JP21H04877, JP22K18630"],"award-info":[{"award-number":["JP21H04877, JP22K18630"]}]},{"name":"Bilateral Program","award":["JPJSBP120239929"],"award-info":[{"award-number":["JPJSBP120239929"]}]},{"name":"the Inamori Research Institute for Science for supporting Yasutaka Kamei via the InaRIS Fellowship","award":[""],"award-info":[{"award-number":[""]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,9,11]]},"DOI":"10.1145\/3650212.3680395","type":"proceedings-article","created":{"date-parts":[[2024,9,11]],"date-time":"2024-09-11T07:44:25Z","timestamp":1726040665000},"page":"1733-1745","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":29,"title":["Large Language Models for Equivalent Mutant Detection: How Far Are We?"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9316-7250","authenticated-orcid":false,"given":"Zhao","family":"Tian","sequence":"first","affiliation":[{"name":"Tianjin University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-7311-7060","authenticated-orcid":false,"given":"Honglin","family":"Shu","sequence":"additional","affiliation":[{"name":"Kyushu University, Fukuoka, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2004-0902","authenticated-orcid":false,"given":"Dong","family":"Wang","sequence":"additional","affiliation":[{"name":"Tianjin University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-6194-8110","authenticated-orcid":false,"given":"Xuejie","family":"Cao","sequence":"additional","affiliation":[{"name":"Tianjin University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7058-1045","authenticated-orcid":false,"given":"Yasutaka","family":"Kamei","sequence":"additional","affiliation":[{"name":"Kyushu University, Fukuoka, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3056-9962","authenticated-orcid":false,"given":"Junjie","family":"Chen","sequence":"additional","affiliation":[{"name":"Tianjin University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,9,11]]},"reference":[{"key":"e_1_3_2_1_2_1","volume-title":"Genetic and Evolutionary Computation\u2013GECCO 2004: Genetic and Evolutionary Computation Conference","author":"Adamopoulos Konstantinos","year":"2004","unstructured":"Konstantinos Adamopoulos, Mark Harman, and Robert M Hierons. 2004. How to overcome the equivalent mutant problem and achieve tailored selective mutation using co-evolution. In Genetic and Evolutionary Computation\u2013GECCO 2004: Genetic and Evolutionary Computation Conference, Seattle, WA, USA, June 26-30, 2004. Proceedings, Part II. 1338\u20131349."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"crossref","unstructured":"Wasi Uddin Ahmad Saikat Chakraborty Baishakhi Ray and Kai-Wei Chang. 2021. Unified pre-training for program understanding and generation. arXiv preprint arXiv:2103.06333.","DOI":"10.18653\/v1\/2021.naacl-main.211"},{"key":"e_1_3_2_1_4_1","unstructured":"Toufique Ahmed Christian Bird Premkumar Devanbu and Saikat Chakraborty. 2024. Studying LLM Performance on Closed-and Open-source Data. arXiv preprint arXiv:2402.15100."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/1062455.1062530"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2006.83"},{"key":"e_1_3_2_1_7_1","unstructured":"Rohan Anil Andrew M Dai Orhan Firat Melvin Johnson Dmitry Lepikhin Alexandre Passos Siamak Shakeri Emanuel Taropa Paige Bailey and Zhifeng Chen. 2023. Palm 2 technical report. arXiv preprint arXiv:2305.10403."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.infsof.2016.01.019"},{"key":"e_1_3_2_1_9_1","volume-title":"2020 IEEE International Conference on Software Testing, Verification and Validation Workshops (ICSTW). 294\u2013303","author":"Baer Michael","year":"2020","unstructured":"Michael Baer, Norbert Oster, and Michael Philippsen. 2020. Mutantdistiller: Using symbolic execution for automatic detection of equivalent mutants and generation of mutant killing tests. In 2020 IEEE International Conference on Software Testing, Verification and Validation Workshops (ICSTW). 294\u2013303."},{"key":"e_1_3_2_1_10_1","volume-title":"2023 IEEE Conference on Software Testing, Verification and Validation (ICST). 222\u2013233","author":"Bartocci Ezio","year":"2023","unstructured":"Ezio Bartocci, Leonardo Mariani, Dejan Ni\u010dkovi\u0107, and Drishti Yadav. 2023. Property-based mutation testing. In 2023 IEEE Conference on Software Testing, Verification and Validation (ICST). 222\u2013233."},{"key":"e_1_3_2_1_11_1","volume-title":"2020 IEEE International Conference on Software Testing, Verification and Validation Workshops (ICSTW). 304\u2013313","author":"Brito Claudinei","year":"2020","unstructured":"Claudinei Brito, Vinicius HS Durelli, Rafael S Durelli, Simone RS de Souza, Auri MR Vincenzi, and M\u00e1rcio Eduardo Delamaro. 2020. A preliminary investigation into using machine learning algorithms to identify minimal and equivalent mutants. In 2020 IEEE International Conference on Software Testing, Verification and Validation Workshops (ICSTW). 304\u2013313."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.12228"},{"key":"e_1_3_2_1_13_1","first-page":"2886","article-title":"Distribution-preserving stratified sampling for learning problems","volume":"29","author":"Cervellera Cristiano","year":"2017","unstructured":"Cristiano Cervellera and Danilo Macci\u00f2. 2017. Distribution-preserving stratified sampling for learning problems. IEEE Transactions on Neural Networks and Learning Systems, 29, 7 (2017), 2886\u20132895.","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"e_1_3_2_1_14_1","volume-title":"Augmenting Equivalent Mutant Dataset Using Symbolic Execution. In 2022 IEEE International Conference on Software Testing, Verification and Validation Workshops (ICSTW). 150\u2013159","author":"Chung Seungjoon","year":"2022","unstructured":"Seungjoon Chung and Shin Yoo. 2022. Augmenting Equivalent Mutant Dataset Using Symbolic Execution. In 2022 IEEE International Conference on Software Testing, Verification and Validation Workshops (ICSTW). 150\u2013159."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jss.2018.03.010"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3611643.3616338"},{"key":"e_1_3_2_1_17_1","volume-title":"Proceedings of the 46th IEEE\/ACM International Conference on Software Engineering. 1\u201313","author":"Feng Sidong","year":"2024","unstructured":"Sidong Feng and Chunyang Chen. 2024. Prompting Is All You Need: Automated Android Bug Replay with Large Language Models. In Proceedings of the 46th IEEE\/ACM International Conference on Software Engineering. 1\u201313."},{"key":"e_1_3_2_1_18_1","volume-title":"Codebert: A pre-trained model for programming and natural languages. arXiv preprint arXiv:2002.08155.","author":"Feng Zhangyin","year":"2020","unstructured":"Zhangyin Feng, Daya Guo, Duyu Tang, Nan Duan, Xiaocheng Feng, Ming Gong, Linjun Shou, Bing Qin, Ting Liu, and Daxin Jiang. 2020. Codebert: A pre-trained model for programming and natural languages. arXiv preprint arXiv:2002.08155."},{"key":"e_1_3_2_1_19_1","volume-title":"Simcse: Simple contrastive learning of sentence embeddings. arXiv preprint arXiv:2104.08821.","author":"Gao Tianyu","year":"2021","unstructured":"Tianyu Gao, Xingcheng Yao, and Danqi Chen. 2021. Simcse: Simple contrastive learning of sentence embeddings. arXiv preprint arXiv:2104.08821."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.infsof.2020.106496"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1142\/S0218194022500322"},{"key":"e_1_3_2_1_22_1","volume-title":"2014 IEEE 25th International Symposium on Software Reliability Engineering. 189\u2013200","author":"Gopinath Rahul","year":"2014","unstructured":"Rahul Gopinath, Carlos Jensen, and Alex Groce. 2014. Mutations: How close are they to real faults? In 2014 IEEE 25th International Symposium on Software Reliability Engineering. 189\u2013200."},{"key":"e_1_3_2_1_23_1","volume-title":"Problem. In 2018 IEEE International Conference on Software Testing, Verification and Validation Workshops (ICSTW). 18\u201324","author":"Gopinath Rahul","year":"2018","unstructured":"Rahul Gopinath, Bj\u00f6rn Mathis, and Andreas Zeller. 2018. If You Can\u2019t Kill a Supermutant, You Have a Problem. In 2018 IEEE International Conference on Software Testing, Verification and Validation Workshops (ICSTW). 18\u201324."},{"key":"e_1_3_2_1_24_1","volume-title":"2020 IEEE 13th International Conference on Software Testing, Validation and Verification (ICST). 198\u2013208","author":"Guimar\u00e3es Marcio Augusto","year":"2020","unstructured":"Marcio Augusto Guimar\u00e3es, Leo Fernandes, M\u00e1rcio Ribeiro, Marcelo d\u2019Amorim, and Rohit Gheyi. 2020. Optimizing mutation testing by discovering dynamic mutant subsumption relations. In 2020 IEEE 13th International Conference on Software Testing, Validation and Verification (ICST). 198\u2013208."},{"key":"e_1_3_2_1_25_1","volume-title":"Unixcoder: Unified cross-modal pre-training for code representation. arXiv preprint arXiv:2203.03850.","author":"Guo Daya","year":"2022","unstructured":"Daya Guo, Shuai Lu, Nan Duan, Yanlin Wang, Ming Zhou, and Jian Yin. 2022. Unixcoder: Unified cross-modal pre-training for code representation. arXiv preprint arXiv:2203.03850."},{"key":"e_1_3_2_1_26_1","volume-title":"Graphcodebert: Pre-training code representations with data flow. arXiv preprint arXiv:2009.08366.","author":"Guo Daya","year":"2020","unstructured":"Daya Guo, Shuo Ren, Shuai Lu, Zhangyin Feng, Duyu Tang, Shujie Liu, Long Zhou, Nan Duan, Alexey Svyatkovskiy, and Shengyu Fu. 2020. Graphcodebert: Pre-training code representations with data flow. arXiv preprint arXiv:2009.08366."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"crossref","unstructured":"Mark Harman Rob Hierons and Sebastian Danicic. 2001. The relationship between program dependence and mutation analysis. Mutation testing for the new century 5\u201313.","DOI":"10.1007\/978-1-4757-5939-6_4"},{"key":"e_1_3_2_1_28_1","volume-title":"2016 IEEE Ninth International Conference on Software Testing, Verification and Validation Workshops (ICSTW). 152\u2013161","author":"Holling Dominik","year":"2016","unstructured":"Dominik Holling, Sebastian Banescu, Marco Probst, Ana Petrovska, and Alexander Pretschner. 2016. Nequivack: Assessing mutation score confidence. In 2016 IEEE Ninth International Conference on Software Testing, Verification and Validation Workshops (ICSTW). 152\u2013161."},{"key":"e_1_3_2_1_29_1","unstructured":"Homepage. 2024. https:\/\/github.com\/tianzhaotju\/EMD"},{"key":"e_1_3_2_1_30_1","volume-title":"Fundamentals of Software Engineering: 7th International Conference, FSEN 2017","author":"Houshmand Mahdi","year":"2017","unstructured":"Mahdi Houshmand and Samad Paydar. 2017. TCE+: An extension of the tce method for detecting equivalent mutants in java programs. In Fundamentals of Software Engineering: 7th International Conference, FSEN 2017, Tehran, Iran, April 26\u201328, 2017, Revised Selected Papers 7. 164\u2013179."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASE56229.2023.00181"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.infsof.2009.04.016"},{"key":"e_1_3_2_1_33_1","volume-title":"An analysis and survey of the development of mutation testing","author":"Jia Yue","year":"2010","unstructured":"Yue Jia and Mark Harman. 2010. An analysis and survey of the development of mutation testing. IEEE transactions on software engineering, 37, 5 (2010), 649\u2013678."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"crossref","unstructured":"Xue Jiang Yihong Dong Lecheng Wang Qiwei Shang and Ge Li. 2023. Self-planning code generation with large language model. arXiv preprint arXiv:2303.06689.","DOI":"10.1145\/3672456"},{"key":"e_1_3_2_1_35_1","volume-title":"Gema Rodr\u00edguez-P\u00e9rez, and Mohamed Sami Shehata.","author":"Khajezade Mohamad","year":"2024","unstructured":"Mohamad Khajezade, Jie Wu, Fatemeh Hendijani Fard, Gema Rodr\u00edguez-P\u00e9rez, and Mohamed Sami Shehata. 2024. Investigating the Efficacy of Large Language Models for Code Clone Detection. arXiv preprint arXiv:2401.13802."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3510417"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2017.2684805"},{"key":"e_1_3_2_1_38_1","volume-title":"2016 IEEE 16th International Working Conference on Source Code Analysis and Manipulation (SCAM). 147\u2013156","author":"Kintis Marinos","year":"2016","unstructured":"Marinos Kintis, Mike Papadakis, Andreas Papadopoulos, Evangelos Valvis, and Nicos Malevris. 2016. Analysing and comparing the effectiveness of mutation testing tools: A manual study. In 2016 IEEE 16th International Working Conference on Source Code Analysis and Manipulation (SCAM). 147\u2013156."},{"key":"e_1_3_2_1_39_1","volume-title":"Machel Reid, Yutaka Matsuo, and Yusuke Iwasawa.","author":"Kojima Takeshi","year":"2022","unstructured":"Takeshi Kojima, Shixiang Shane Gu, Machel Reid, Yutaka Matsuo, and Yusuke Iwasawa. 2022. Large language models are zero-shot reasoners. Advances in neural information processing systems, 35 (2022), 22199\u201322213."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1952.10483441"},{"key":"e_1_3_2_1_41_1","volume-title":"2019 IEEE International Conference on Software Testing, Verification and Validation Workshops (ICSTW). 77\u201382","author":"Kushigian Benjamin","year":"2019","unstructured":"Benjamin Kushigian, Amit Rawat, and Ren\u00e9 Just. 2019. Medusa: Mutant equivalence detection using satisfiability analysis. In 2019 IEEE International Conference on Software Testing, Verification and Validation Workshops (ICSTW). 77\u201382."},{"key":"e_1_3_2_1_42_1","volume-title":"Yangtian Zi, Niklas Muennighoff, Denis Kocetkov, Chenghao Mou, Marc Marone, Christopher Akiki, Jia Li, and Jenny Chim.","author":"Li Raymond","year":"2023","unstructured":"Raymond Li, Loubna Ben Allal, Yangtian Zi, Niklas Muennighoff, Denis Kocetkov, Chenghao Mou, Marc Marone, Christopher Akiki, Jia Li, and Jenny Chim. 2023. StarCoder: may the source be with you!. arXiv preprint arXiv:2305.06161."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASE56229.2023.00089"},{"key":"e_1_3_2_1_44_1","first-page":"4328","article-title":"Diffusion-lm improves controllable text generation","volume":"35","author":"Li Xiang","year":"2022","unstructured":"Xiang Li, John Thickstun, Ishaan Gulrajani, Percy S Liang, and Tatsunori B Hashimoto. 2022. Diffusion-lm improves controllable text generation. Advances in Neural Information Processing Systems, 35 (2022), 4328\u20134343.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_45_1","volume-title":"Yuyao Wang, and Lingming Zhang.","author":"Liu Jiawei","year":"2024","unstructured":"Jiawei Liu, Chunqiu Steven Xia, Yuyao Wang, and Lingming Zhang. 2024. Is your code generated by chatgpt really correct? rigorous evaluation of large language models for code generation. Advances in Neural Information Processing Systems, 36 (2024)."},{"key":"e_1_3_2_1_46_1","first-page":"1","article-title":"Pre-train, prompt, and predict: A systematic survey of prompting methods in natural language processing","volume":"55","author":"Liu Pengfei","year":"2023","unstructured":"Pengfei Liu, Weizhe Yuan, Jinlan Fu, Zhengbao Jiang, Hiroaki Hayashi, and Graham Neubig. 2023. Pre-train, prompt, and predict: A systematic survey of prompting methods in natural language processing. Comput. Surveys, 55, 9 (2023), 1\u201335.","journal-title":"Comput. Surveys"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISSRE.2015.7381798"},{"key":"e_1_3_2_1_48_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, and Duyu Tang. 2021. Codexglue: A machine learning benchmark dataset for code understanding and generation. arXiv preprint arXiv:2102.04664."},{"key":"e_1_3_2_1_49_1","volume-title":"International Conference on Machine Learning. 7145\u20137155","author":"Lu Yucheng","year":"2021","unstructured":"Yucheng Lu, Youngsuk Park, Lifan Chen, Yuyang Wang, Christopher De Sa, and Dean Foster. 2021. Variance reduced training with stratified sampling for forecasting models. In International Conference on Machine Learning. 7145\u20137155."},{"key":"e_1_3_2_1_50_1","unstructured":"Wei Ma Shangqing Liu Wenhan Wang Qiang Hu Ye Liu Cen Zhang Liming Nie and Yang Liu. 2023. The scope of chatgpt in software engineering: A thorough investigation. arXiv preprint arXiv:2305.12138."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2013.44"},{"key":"e_1_3_2_1_52_1","volume-title":"Proceedings of the 31st ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering. 262\u2013274","author":"Moghadam Mohsen Moradi","year":"2023","unstructured":"Mohsen Moradi Moghadam, Mehdi Bagherzadeh, Raffi Khatchadourian, and Hamid Bagheri. 2023. muAkka: Mutation Testing for Actor Concurrency in Akka using Real-World Bugs. In Proceedings of the 31st ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering. 262\u2013274."},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1002\/smr.2238"},{"key":"e_1_3_2_1_54_1","unstructured":"Changan Niu Chuanyi Li Vincent Ng Dongxiao Chen Jidong Ge and Bin Luo. 2023. An empirical comparison of pre-trained models of source code. arXiv preprint arXiv:2302.04026."},{"key":"e_1_3_2_1_55_1","volume-title":"Automatically detecting equivalent mutants and infeasible paths. Software testing, verification and reliability, 7, 3","author":"Jefferson Offutt A","year":"1997","unstructured":"A Jefferson Offutt and Jie Pan. 1997. Automatically detecting equivalent mutants and infeasible paths. Software testing, verification and reliability, 7, 3 (1997), 165\u2013192."},{"key":"e_1_3_2_1_56_1","volume-title":"2021 IEEE International Conference on Software Testing, Verification and Validation Workshops (ICSTW). 19\u201324","author":"Oh Saeyoon","year":"2021","unstructured":"Saeyoon Oh, Seongmin Lee, and Shin Yoo. 2021. Effectively sampling higher order mutants using causal effect. In 2021 IEEE International Conference on Software Testing, Verification and Validation Workshops (ICSTW). 19\u201324."},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1145\/3530786"},{"key":"e_1_3_2_1_58_1","unstructured":"OpenAI. 2022. ChatGPT: Optimizing Language Models for Dialogue.. https:\/\/openai.com\/blog\/chatgpt"},{"key":"e_1_3_2_1_59_1","unstructured":"OpenAI. 2024. https:\/\/openai.com\/"},{"key":"e_1_3_2_1_60_1","unstructured":"OpenAI. 2024. New Generation of Embedding Model. https:\/\/openai.com\/blog\/new-embedding-models-and-api-updates"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.scico.2014.05.012"},{"key":"e_1_3_2_1_62_1","volume-title":"2015 IEEE\/ACM 37th IEEE International Conference on Software Engineering. 1, 936\u2013946","author":"Papadakis Mike","year":"2015","unstructured":"Mike Papadakis, Yue Jia, Mark Harman, and Yves Le Traon. 2015. Trivial compiler equivalence: A large scale empirical study of a simple, fast and effective equivalent mutant detection technique. In 2015 IEEE\/ACM 37th IEEE International Conference on Software Engineering. 1, 936\u2013946."},{"key":"e_1_3_2_1_63_1","volume-title":"Yves Le Traon, and Mark Harman","author":"Papadakis Mike","year":"2019","unstructured":"Mike Papadakis, Marinos Kintis, Jie Zhang, Yue Jia, Yves Le Traon, and Mark Harman. 2019. Mutation testing advances: an analysis and survey. In Advances in computers. 112, Elsevier, 275\u2013378."},{"key":"e_1_3_2_1_64_1","volume-title":"Proceedings of the 28th Annual ACM Symposium on Applied Computing. 1223\u20131229","author":"Papadakis Mike","year":"2013","unstructured":"Mike Papadakis and Yves Le Traon. 2013. Mutation testing strategies using mutant classification. In Proceedings of the 28th Annual ACM Symposium on Applied Computing. 1223\u20131229."},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1002\/stvr.1509"},{"key":"e_1_3_2_1_66_1","volume-title":"2021 IEEE International Conference on Software Testing, Verification and Validation Workshops (ICSTW). 13\u201318","author":"Peacock Samuel","year":"2021","unstructured":"Samuel Peacock, Lin Deng, Josh Dehlinger, and Suranjan Chakraborty. 2021. Automatic equivalent mutants classification using abstract syntax tree neural networks. In 2021 IEEE International Conference on Software Testing, Verification and Validation Workshops (ICSTW). 13\u201318."},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1145\/3533767.3534217"},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1145\/3276517"},{"key":"e_1_3_2_1_69_1","volume-title":"Yossi Adi, Jingyu Liu, Tal Remez, and J\u00e9r\u00e9my Rapin.","author":"Roziere Baptiste","year":"2023","unstructured":"Baptiste Roziere, Jonas Gehring, Fabian Gloeckle, Sten Sootla, Itai Gat, Xiaoqing Ellen Tan, Yossi Adi, Jingyu Liu, Tal Remez, and J\u00e9r\u00e9my Rapin. 2023. Code llama: Open foundation models for code. arXiv preprint arXiv:2308.12950."},{"key":"e_1_3_2_1_70_1","volume-title":"Proceedings of the 2024 ACM\/IEEE 44th International Conference on Software Engineering: New Ideas and Emerging Results. 102\u2013106","author":"Sallou June","year":"2024","unstructured":"June Sallou, Thomas Durieux, and Annibale Panichella. 2024. Breaking the silence: the threats of using llms in software engineering. In Proceedings of the 2024 ACM\/IEEE 44th International Conference on Software Engineering: New Ideas and Emerging Results. 102\u2013106."},{"key":"e_1_3_2_1_71_1","article-title":"An empirical evaluation of using large language models for automated unit test generation","author":"Sch\u00e4fer Max","year":"2023","unstructured":"Max Sch\u00e4fer, Sarah Nadi, Aryaz Eghbali, and Frank Tip. 2023. An empirical evaluation of using large language models for automated unit test generation. IEEE Transactions on Software Engineering.","journal-title":"IEEE Transactions on Software Engineering."},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICST.2010.30"},{"key":"e_1_3_2_1_73_1","doi-asserted-by":"publisher","DOI":"10.1002\/stvr.1473"},{"key":"e_1_3_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.1145\/3293882.3330568"},{"key":"e_1_3_2_1_75_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00280"},{"key":"e_1_3_2_1_76_1","unstructured":"Zhao Tian and Junjie Chen. 2023. Test-case-driven programming understanding in large language models for better code generation. arXiv preprint arXiv:2309.16120."},{"key":"e_1_3_2_1_77_1","volume-title":"2023 38th IEEE\/ACM International Conference on Automated Software Engineering (ASE). 850\u2013862","author":"Tian Zhao","year":"2023","unstructured":"Zhao Tian, Junjie Chen, and Zhi Jin. 2023. Code difference guided adversarial example generation for deep code models. In 2023 38th IEEE\/ACM International Conference on Automated Software Engineering (ASE). 850\u2013862."},{"key":"e_1_3_2_1_78_1","volume-title":"2023 38th IEEE\/ACM International Conference on Automated Software Engineering (ASE). 560\u2013572","author":"Tian Zhao","year":"2023","unstructured":"Zhao Tian, Junjie Chen, and Xiangyu Zhang. 2023. On-the-fly improving performance of deep code models via input denoising. In 2023 38th IEEE\/ACM International Conference on Automated Software Engineering (ASE). 560\u2013572."},{"key":"e_1_3_2_1_79_1","doi-asserted-by":"publisher","DOI":"10.1145\/3551349.3556949"},{"key":"e_1_3_2_1_80_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10664-019-09778-7"},{"key":"e_1_3_2_1_81_1","volume-title":"Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971.","author":"Touvron Hugo","year":"2023","unstructured":"Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timoth\u00e9e Lacroix, Baptiste Rozi\u00e8re, Naman Goyal, Eric Hambro, and Faisal Azhar. 2023. Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971."},{"key":"e_1_3_2_1_82_1","volume-title":"2019 IEEE International conference on software maintenance and evolution (ICSME). 301\u2013312","author":"Tufano Michele","year":"2019","unstructured":"Michele Tufano, Cody Watson, Gabriele Bavota, Massimiliano Di Penta, Martin White, and Denys Poshyvanyk. 2019. Learning how to mutate source code from bug-fixes. In 2019 IEEE International conference on software maintenance and evolution (ICSME). 301\u2013312."},{"key":"e_1_3_2_1_83_1","article-title":"Visualizing Data using t-SNE","author":"van der Maaten Laurens","year":"2008","unstructured":"Laurens van der Maaten and Geoffrey E. Hinton. 2008. Visualizing Data using t-SNE. Journal of Machine Learning Research.","journal-title":"Journal of Machine Learning Research."},{"key":"e_1_3_2_1_84_1","volume-title":"2021 IEEE International Conference on Software Testing, Verification and Validation Workshops (ICSTW). 7\u201312","author":"van Hijfte Lars","year":"2021","unstructured":"Lars van Hijfte and Ana Oprescu. 2021. Mutantbench: an equivalent mutant problem comparison framework. In 2021 IEEE International Conference on Software Testing, Verification and Validation Workshops (ICSTW). 7\u201312."},{"key":"e_1_3_2_1_85_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2024.3368208"},{"key":"e_1_3_2_1_86_1","volume-title":"Nghi DQ Bui, Junnan Li, and Steven CH Hoi.","author":"Wang Yue","year":"2023","unstructured":"Yue Wang, Hung Le, Akhilesh Deepak Gotmare, Nghi DQ Bui, Junnan Li, and Steven CH Hoi. 2023. Codet5+: Open code large language models for code understanding and generation. arXiv preprint arXiv:2305.07922."},{"key":"e_1_3_2_1_87_1","doi-asserted-by":"crossref","unstructured":"Yue Wang Weishi Wang Shafiq Joty and Steven CH Hoi. 2021. Codet5: Identifier-aware unified pre-trained encoder-decoder models for code understanding and generation. arXiv preprint arXiv:2109.00859.","DOI":"10.18653\/v1\/2021.emnlp-main.685"},{"key":"e_1_3_2_1_88_1","volume-title":"Chi, Quoc V Le, and Denny Zhou","author":"Wei Jason","year":"2022","unstructured":"Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V Le, and Denny Zhou. 2022. Chain-of-thought prompting elicits reasoning in large language models. Advances in neural information processing systems, 35 (2022), 24824\u201324837."},{"key":"e_1_3_2_1_89_1","doi-asserted-by":"crossref","unstructured":"Thomas Wolf Lysandre Debut Victor Sanh Julien Chaumond Clement Delangue Anthony Moi Pierric Cistac Tim Rault R\u00e9mi Louf and Morgan Funtowicz. 2019. Huggingface\u2019s transformers: State-of-the-art natural language processing. arXiv preprint arXiv:1910.03771.","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"e_1_3_2_1_90_1","volume-title":"Michael Pradel, and Lingming Zhang.","author":"Xia Chunqiu Steven","year":"2023","unstructured":"Chunqiu Steven Xia, Matteo Paltenghi, Jia Le Tian, Michael Pradel, and Lingming Zhang. 2023. Universal fuzzing via large language models. arXiv preprint arXiv:2308.04748."},{"key":"e_1_3_2_1_91_1","unstructured":"Chen Yang Junjie Chen Bin Lin Jianyi Zhou and Ziqi Wang. 2024. Enhancing LLM-based Test Generation for Hard-to-Cover Branches via Program Analysis. arXiv preprint arXiv:2404.04966."},{"key":"e_1_3_2_1_92_1","unstructured":"Lin Yang Chen Yang Shutao Gao Weijing Wang Bo Wang Qihao Zhu Xiao Chu Jianyi Zhou Guangtai Liang and Qianxiang Wang. 2024. An Empirical Study of Unit Test Generation with Large Language Models. arXiv preprint arXiv:2406.18181."},{"key":"e_1_3_2_1_93_1","volume-title":"Proceedings of the 36th international conference on software engineering. 919\u2013930","author":"Yao Xiangjuan","year":"2014","unstructured":"Xiangjuan Yao, Mark Harman, and Yue Jia. 2014. A study of equivalent and stubborn mutation operators using human analysis of equivalence. In Proceedings of the 36th international conference on software engineering. 919\u2013930."},{"key":"e_1_3_2_1_94_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE.2019.00086"},{"key":"e_1_3_2_1_95_1","volume-title":"Ferdian Thung, and David Lo.","author":"Zhang Ting","year":"2023","unstructured":"Ting Zhang, Ivana Clairine Irsan, Ferdian Thung, and David Lo. 2023. Revisiting sentiment analysis for software engineering in the era of large language models. arXiv preprint arXiv:2310.11113."}],"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\/3650212.3680395","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3650212.3680395","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T20:58:09Z","timestamp":1750280289000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3650212.3680395"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,11]]},"references-count":94,"alternative-id":["10.1145\/3650212.3680395","10.1145\/3650212"],"URL":"https:\/\/doi.org\/10.1145\/3650212.3680395","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"}}]}}