{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T05:46:10Z","timestamp":1776750370342,"version":"3.51.2"},"reference-count":68,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62402113"],"award-info":[{"award-number":["62402113"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"General Program of the Natural Science Foundation of Guangdong Province, China","award":["2025A1515011631"],"award-info":[{"award-number":["2025A1515011631"]}]},{"name":"Shenzhen Science and Technology Program","award":["JCYJ20240813150107010"],"award-info":[{"award-number":["JCYJ20240813150107010"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IIEEE Trans. Software Eng."],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1109\/tse.2026.3657353","type":"journal-article","created":{"date-parts":[[2026,1,23]],"date-time":"2026-01-23T20:58:33Z","timestamp":1769201913000},"page":"1215-1233","source":"Crossref","is-referenced-by-count":0,"title":["Are Decoder-Only Large Language Models the Silver Bullet for Code Search?"],"prefix":"10.1109","volume":"52","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3298-2008","authenticated-orcid":false,"given":"Yuxuan","family":"Chen","sequence":"first","affiliation":[{"name":"School of Software Engineering, Sun Yat-sen University, Zhuhai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3462-997X","authenticated-orcid":false,"given":"Mingwei","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Software Engineering, Sun Yat-sen University, Zhuhai, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-5340-4896","authenticated-orcid":false,"given":"Guangsheng","family":"Ou","sequence":"additional","affiliation":[{"name":"School of Software Engineering, Sun Yat-sen University, Zhuhai, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-4881-4148","authenticated-orcid":false,"given":"Anji","family":"Li","sequence":"additional","affiliation":[{"name":"School of Software Engineering, Sun Yat-sen University, Zhuhai, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-1452-8562","authenticated-orcid":false,"given":"Dekun","family":"Dai","sequence":"additional","affiliation":[{"name":"School of Software Engineering, Sun Yat-sen University, Zhuhai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7761-7269","authenticated-orcid":false,"given":"Yanlin","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Software Engineering, Sun Yat-sen University, Zhuhai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7872-7718","authenticated-orcid":false,"given":"Zibin","family":"Zheng","sequence":"additional","affiliation":[{"name":"School of Software Engineering, Sun Yat-sen University, Zhuhai, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3628161"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s10664-024-10602-0"},{"key":"ref3","article-title":"ChatGPT: Optimizing language models for dialogue","year":"2025"},{"key":"ref4","article-title":"DeepSeek-Coder: When the large language model meets programming\u2013the rise of code intelligence","author":"Guo","year":"2024"},{"key":"ref5","article-title":"Retrieval-augmented generation for large language models: A survey","author":"Gao","year":"2023"},{"key":"ref6","article-title":"Program synthesis with large language models","author":"Austin","year":"2021"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE48619.2023.00185"},{"key":"ref8","article-title":"GraphCodeBERT: Pre-training code representations with data flow","author":"Guo","year":"2020"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.139"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.499"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.211"},{"key":"ref12","article-title":"Evaluating large language models trained on code","author":"Chen","year":"2021"},{"key":"ref13","article-title":"Scaling language models: Methods, analysis & insights from training gopher","author":"Rae","year":"2021"},{"key":"ref14","article-title":"A survey of large language models for code: Evolution, benchmarking, and future trends","author":"Zheng","year":"2023"},{"key":"ref15","article-title":"DeepSeek LLM: Scaling open-source language models with longtermism","author":"Bi","year":"2024"},{"key":"ref16","article-title":"Code LLAMA: Open foundation models for code","author":"Roziere","year":"2023"},{"key":"ref17","article-title":"DecoderLLMs-CodeSearch: Replication package","author":"Chen","year":"2025"},{"key":"ref18","article-title":"Are decoder-only LLMs the silver bullet? (collection)","year":"2025"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-00593-0_26"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3180155.3180167"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3485275"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380295"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3387904.3389269"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICSME46990.2020.00021"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3387904.3389278"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ASE.2019.00012"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3447571"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482127"},{"key":"ref29","first-page":"883","article-title":"OCOR: An overlapping-aware code retriever","volume-title":"Proc. 35th IEEE\/ACM Int. Conf. Automated Softw. Eng.","author":"Zhu","year":"2020"},{"key":"ref30","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"ref31","article-title":"CodeSearchNet challenge: Evaluating the state of semantic code search","author":"Husain","year":"2019"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462840"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3510003.3510160"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.685"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/icse48619.2023.00180"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657951"},{"key":"ref37","article-title":"LLAMA 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.642"},{"key":"ref39","article-title":"Repetition improves language model embeddings","author":"Springer","year":"2024"},{"key":"ref40","article-title":"Llm2vec: Large language models are secretly powerful text encoders","author":"BehnamGhader","year":"2024"},{"key":"ref41","article-title":"CoSQA+: Enhancing code search dataset with matching code","author":"Gong","year":"2024"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.442"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3178876.3186081"},{"key":"ref44","first-page":"77","article-title":"The trec-8 question answering track report","volume":"99","author":"Voorhees","year":"1999","journal-title":"TREC"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3295776"},{"key":"ref46","article-title":"Mistral 7b","author":"Jiang","year":"2023"},{"key":"ref47","article-title":"Speechless-code-mistral-7b-v1.0","year":"2025"},{"key":"ref48","article-title":"Platypus: Quick, cheap, and powerful refinement of LLMs","author":"Lee","year":"2023"},{"key":"ref49","article-title":"OpenOrca: An open dataset of GPT augmented flan reasoning traces","author":"Lian","year":"2025"},{"key":"ref50","article-title":"WizarDLM: Empowering large pre-trained language models to follow complex instructions","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Xu","year":"2024"},{"key":"ref51","article-title":"Gemma: Open models based on Gemini research and technology","author":"Team","year":"2024"},{"key":"ref52","article-title":"CodeGemma: Open code models based on gemma","author":"Team","year":"2024"},{"key":"ref53","article-title":"The LLAMA 3 herd of models","author":"Grattafiori","year":"2024"},{"key":"ref54","article-title":"StarCoder 2 and the stack v2: The next generation","author":"Lozhkov","year":"2024"},{"key":"ref55","article-title":"Qwen2. 5-coder technical report","author":"Hui","year":"2024"},{"key":"ref56","article-title":"Roberta: A robustly optimized BERT pretraining approach","author":"Liu","year":"2019"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.18"},{"key":"ref58","article-title":"MTEB leaderboard","year":"2025"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.552"},{"key":"ref60","article-title":"Qwen2.5-coder","year":"2025"},{"key":"ref61","article-title":"Language models are few-shot learners","author":"Mann","year":"2020"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/3726302.3730059"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/3711896.3737029"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/3726302.3730029"},{"key":"ref65","article-title":"LLMs are also effective embedding models: An in-depth overview","author":"Tao","year":"2024"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.1132"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-acl.673"},{"key":"ref68","article-title":"Code generation on MBPP","year":"2024"}],"container-title":["IEEE Transactions on Software Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/32\/11488173\/11361403.pdf?arnumber=11361403","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T05:17:23Z","timestamp":1776748643000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11361403\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":68,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tse.2026.3657353","relation":{},"ISSN":["0098-5589","1939-3520","2326-3881"],"issn-type":[{"value":"0098-5589","type":"print"},{"value":"1939-3520","type":"electronic"},{"value":"2326-3881","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4]]}}}