{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T18:44:28Z","timestamp":1791917068277,"version":"4.3.4"},"reference-count":66,"publisher":"Association for Computing Machinery (ACM)","issue":"5","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62402506, No. 62474196"],"award-info":[{"award-number":["62402506, No. 62474196"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Research Foundation from NUDT","award":["ZK24-05"],"award-info":[{"award-number":["ZK24-05"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Softw. Eng. Methodol."],"published-print":{"date-parts":[[2026,5,31]]},"abstract":"<jats:p>\n                    The software development process is characterized by an iterative cycle of continuous functionality implementation and debugging, essential for the enhancement of software quality and adaptability to changing requirements. This process incorporates two isolatedly studied tasks: Code Search (CS), which retrieves reference code from a code corpus to aid in code implementation, and Fault Localization (FL), which identifies code entities responsible for bugs within the software project to boost software debugging. The basic observation of this study is that these two tasks exhibit similarities since they both address search problems. Notably, CS techniques have demonstrated greater effectiveness than FL ones, possibly because of the precise semantic details of the required code offered by natural language queries, which are not readily accessible to FL methods. Drawing inspiration from this, we hypothesize that a fault localizer could achieve greater proficiency if semantic information about the buggy methods were made available. Based on this idea, we propose\n                    <jats:inline-formula content-type=\"math\/tex\">\n                      <jats:tex-math notation=\"LaTeX\" version=\"MathJax\">\\(\\texttt{CosFL}\\)<\/jats:tex-math>\n                    <\/jats:inline-formula>\n                    , an FL approach that decomposes the FL task into two steps:\n                    <jats:italic toggle=\"yes\">query generation<\/jats:italic>\n                    , which describes the functionality of the problematic code in natural language, and\n                    <jats:italic toggle=\"yes\">fault retrieval<\/jats:italic>\n                    , which uses CS to find program elements semantically related to the query, allowing for finishing the FL task from a CS perspective. Specifically, to depict the buggy functionalities and generate high-quality queries,\n                    <jats:inline-formula content-type=\"math\/tex\">\n                      <jats:tex-math notation=\"LaTeX\" version=\"MathJax\">\\(\\texttt{CosFL}\\)<\/jats:tex-math>\n                    <\/jats:inline-formula>\n                    extensively harnesses the code analysis, semantic comprehension, text generation, and decision-making capabilities of LLMs. Moreover, to enhance the accuracy of CS,\n                    <jats:inline-formula content-type=\"math\/tex\">\n                      <jats:tex-math notation=\"LaTeX\" version=\"MathJax\">\\(\\texttt{CosFL}\\)<\/jats:tex-math>\n                    <\/jats:inline-formula>\n                    captures varying levels of context information and employs a multi-granularity CS strategy, which facilitates a more precise identification of buggy methods from a holistic view. The evaluation on 835 real bugs from 23 Java projects shows that\n                    <jats:inline-formula content-type=\"math\/tex\">\n                      <jats:tex-math notation=\"LaTeX\" version=\"MathJax\">\\(\\texttt{CosFL}\\)<\/jats:tex-math>\n                    <\/jats:inline-formula>\n                    successfully localizes 324 bugs within Top-1, which significantly outperforms the state-of-the-art approaches by 26.6%\u201357.3%. The ablation study and sensitivity analysis further validate the importance of different components and the robustness of\n                    <jats:inline-formula content-type=\"math\/tex\">\n                      <jats:tex-math notation=\"LaTeX\" version=\"MathJax\">\\(\\texttt{CosFL}\\)<\/jats:tex-math>\n                    <\/jats:inline-formula>\n                    across different backend models.\n                  <\/jats:p>","DOI":"10.1145\/3757915","type":"journal-article","created":{"date-parts":[[2025,8,26]],"date-time":"2025-08-26T15:44:59Z","timestamp":1756223099000},"page":"1-32","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":12,"title":["Fault Localization from the Semantic Code Search Perspective"],"prefix":"10.1145","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-3440-9520","authenticated-orcid":false,"given":"Yihao","family":"Qin","sequence":"first","affiliation":[{"name":"College of Computer Science and Technology, National University of Defense Technology, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1469-2063","authenticated-orcid":false,"given":"Shangwen","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, National University of Defense Technology, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4504-6806","authenticated-orcid":false,"given":"Yan","family":"Lei","sequence":"additional","affiliation":[{"name":"School of Big Data &amp; Software Engineering, Chongqing University, Chongqing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3243-1019","authenticated-orcid":false,"given":"Zhuo","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tianjin University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5905-4677","authenticated-orcid":false,"given":"Bo","family":"Lin","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, National University of Defense Technology, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8642-8582","authenticated-orcid":false,"given":"Xin","family":"Peng","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, National University of Defense Technology, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3794-9434","authenticated-orcid":false,"given":"Jun","family":"Ma","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, National University of Defense Technology, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8084-8009","authenticated-orcid":false,"given":"Liqian","family":"Chen","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, National University of Defense Technology, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4204-7424","authenticated-orcid":false,"given":"Xiaoguang","family":"Mao","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, National University of Defense Technology, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,4,24]]},"reference":[{"key":"e_1_3_2_2_2","unstructured":"Sample Size Calculator. 2024. Retrieved from https:\/\/www.surveysystem.com\/sscalc.htm"},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/PRDC.2006.18"},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.5555\/1308173.1308264"},{"key":"e_1_3_2_5_2","unstructured":"Josh Achiam Steven Adler Sandhini Agarwal Lama Ahmad Ilge Akkaya Florencia Leoni Aleman Diogo Almeida Janko Altenschmidt Sam Altman Shyamal Anadkat et al. 2024. GPT-4 Technical Report. arXiv:2303.08774. Retrieved from https:\/\/arxiv.org\/abs\/2303.08774"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1145\/3551349.3559555"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1002\/widm.1178"},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1145\/3106237.3106255"},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1145\/3655103.3655110"},{"key":"e_1_3_2_10_2","unstructured":"ChromaDB. 2024. Retrieved from https:\/\/github.com\/chroma-core\/chroma"},{"key":"e_1_3_2_11_2","unstructured":"DeepSeek. 2024. DeepSeek-V2.5-1210. Retrieved from https:\/\/huggingface.co\/deepseek-ai\/DeepSeek-V2.5-1210"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1145\/3611643.3616338"},{"key":"e_1_3_2_13_2","unstructured":"Darren Edge Ha Trinh Newman Cheng Joshua Bradley Alex Chao Apurva Mody Steven Truitt and Jonathan Larson. 2024. From local to global: A graph rag approach to query-focused summarization. arXiv:2404.16130. Retrieved from https:\/\/arxiv.org\/abs\/2404.16130"},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00355-011-0603-9"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1145\/3180155.3180167"},{"key":"e_1_3_2_16_2","volume-title":"International Symposium on Applied Corporate Computing","author":"Hitz Martin","year":"1995","unstructured":"Martin Hitz and Behzad Montazeri. 1995. Measuring coupling and cohesion in object-oriented systems. In International Symposium on Applied Corporate Computing."},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2022.08.024"},{"key":"e_1_3_2_18_2","unstructured":"JavaAPI. 2024. Instrument. Retrieved from https:\/\/docs.oracle.com\/javase\/8\/docs\/api\/java\/lang\/instrument\/package-summary.html"},{"key":"e_1_3_2_19_2","unstructured":"JGraphT. 2024. JGraphT. Retrieved from https:\/\/jgrapht.org"},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2022.3177713"},{"key":"e_1_3_2_21_2","unstructured":"Haolin Jin Linghan Huang Haipeng Cai Jun Yan Bo Li and Huaming Chen. 2024. From LLMs to LLM-based agents for software engineering: A survey of current challenges and future. arXiv:2408.02479. Retrieved from https:\/\/arxiv.org\/abs\/2408.02479"},{"key":"e_1_3_2_22_2","unstructured":"JinaAI. 2024. Jina Embeddings. Retrieved from https:\/\/jina.ai\/embeddings"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1145\/2610384.2628055"},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1145\/3660771"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1207\/s15327051hci0304_2"},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1145\/2931037.2931051"},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1145\/83880.84459"},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2008.90"},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1145\/3293882.3330574"},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1145\/3133916"},{"key":"e_1_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1145\/3540250.3549137"},{"key":"e_1_3_2_32_2","volume-title":"International Conference on Learning Representations (ICLR \u201916)","author":"Li Yujia","year":"2016","unstructured":"Yujia Li, Richard Zemel, Marc Brockschmidt, and Daniel Tarlow. 2016. Gated graph sequence neural networks. In International Conference on Learning Representations (ICLR \u201916)."},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00638"},{"key":"e_1_3_2_34_2","unstructured":"LlamaIndex. 2024. Retrieved from https:\/\/github.com\/run-llama\/llama_index"},{"key":"e_1_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1145\/3468264.3468580"},{"key":"e_1_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1145\/3597503.3639187"},{"key":"e_1_3_2_37_2","unstructured":"OpenAI. 2024. Retrieved from https:\/\/openai.com"},{"key":"e_1_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1002\/stvr.1509"},{"key":"e_1_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.5555\/1639537.1639542"},{"key":"e_1_3_2_40_2","unstructured":"Yihao Qin Shangwen Wang Yiling Lou Jinhao Dong Kaixin Wang Xiaoling Li and Xiaoguang Mao. 2024. AgentFL: Scaling LLM-based fault localization to project-level context. arXiv:2403.16362. Retrieved from https:\/\/arxiv.org\/abs\/2403.16362"},{"key":"e_1_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.5555\/3367471.3367705"},{"key":"e_1_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.scico.2009.02.007"},{"key":"e_1_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/ASE.2013.6693093"},{"key":"e_1_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE48619.2023.00185"},{"key":"e_1_3_2_45_2","first-page":"1","article-title":"A comparison of semantic similarity methods for maximum human interpretability","volume":"1","author":"Sitikhu Pinky","year":"2019","unstructured":"Pinky Sitikhu, Kritish Pahi, Pujan Thapa, and Subarna Shakya. 2019. A comparison of semantic similarity methods for maximum human interpretability. In 2019 Artificial Intelligence for Transforming Business and Society (AITB), Vol. 1, 1\u20134.","journal-title":"2019 Artificial Intelligence for Transforming Business and Society (AITB)"},{"key":"e_1_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.1109\/SANER.2018.8330203"},{"key":"e_1_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1145\/3092703.3092717"},{"key":"e_1_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.1145\/3656341"},{"key":"e_1_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-2057"},{"key":"e_1_3_2_50_2","doi-asserted-by":"crossref","first-page":"1045","DOI":"10.21437\/Interspeech.2010-343","article-title":"Recurrent neural network based language model","author":"Tom\u00e1\u015d Mikolov","year":"2010","unstructured":"Mikolov Tom\u00e1\u015d, Karafi\u00e1t Martin, Burget Luk\u00e1\u015d, \u0108ernock\u00fd Jan, and Khudanpur Sanjeev. 2010. Recurrent neural network based language model. In Interspeech 2010, 1045.","journal-title":"Interspeech 2010"},{"key":"e_1_3_2_51_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-019-41695-z"},{"key":"e_1_3_2_52_2","unstructured":"treesitter. 2024. tree-sitter. Retrieved from https:\/\/tree-sitter.github.io\/tree-sitter"},{"key":"e_1_3_2_53_2","unstructured":"VoyageAI. 2024. Retrieved from https:\/\/www.voyageai.com\/"},{"key":"e_1_3_2_54_2","doi-asserted-by":"publisher","DOI":"10.1145\/3664597"},{"key":"e_1_3_2_55_2","doi-asserted-by":"publisher","DOI":"10.1145\/2771783.2771797"},{"key":"e_1_3_2_56_2","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2024.3403042"},{"key":"e_1_3_2_57_2","doi-asserted-by":"publisher","DOI":"10.1145\/3622815"},{"key":"e_1_3_2_58_2","doi-asserted-by":"publisher","DOI":"10.1109\/TR.2013.2285319"},{"key":"e_1_3_2_59_2","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2016.2521368"},{"key":"e_1_3_2_60_2","doi-asserted-by":"publisher","DOI":"10.1002\/9781119880929.ch1"},{"key":"e_1_3_2_61_2","doi-asserted-by":"publisher","DOI":"10.1145\/2348283.2348315"},{"key":"e_1_3_2_62_2","unstructured":"Yonghao Wu Zheng Li Jie M. Zhang Mike Papadakis Mark Harman and Yong Liu. 2023. Large language models in fault localisation. arXiv:2308.15276. Retrieved from https:\/\/arxiv.org\/abs\/2308.15276"},{"key":"e_1_3_2_63_2","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645336"},{"key":"e_1_3_2_64_2","unstructured":"John Yang Carlos E. Jimenez Alexander Wettig Kilian Lieret Shunyu Yao Karthik Narasimhan and Ofir Press. 2024. Swe-agent: Agent-computer interfaces enable automated software engineering. arXiv:2405.15793. Retrieved from https:\/\/arxiv.org\/abs\/2405.15793"},{"key":"e_1_3_2_65_2","doi-asserted-by":"publisher","DOI":"10.1109\/SANER.2019.8668002"},{"key":"e_1_3_2_66_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE.2012.6227210"},{"key":"e_1_3_2_67_2","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2019.2892102"}],"container-title":["ACM Transactions on Software Engineering and Methodology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3757915","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T06:33:09Z","timestamp":1777098789000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3757915"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,24]]},"references-count":66,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2026,5,31]]}},"alternative-id":["10.1145\/3757915"],"URL":"https:\/\/doi.org\/10.1145\/3757915","relation":{},"ISSN":["1049-331X","1557-7392"],"issn-type":[{"value":"1049-331X","type":"print"},{"value":"1557-7392","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,24]]},"assertion":[{"value":"2024-12-25","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-07-27","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-04-24","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}