{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,11]],"date-time":"2025-06-11T04:10:24Z","timestamp":1749615024557,"version":"3.41.0"},"reference-count":57,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2025,6,10]],"date-time":"2025-06-10T00:00:00Z","timestamp":1749513600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,6,10]],"date-time":"2025-06-10T00:00:00Z","timestamp":1749513600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Supercomput"],"DOI":"10.1007\/s11227-025-07487-1","type":"journal-article","created":{"date-parts":[[2025,6,10]],"date-time":"2025-06-10T15:55:20Z","timestamp":1749570920000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["UCP: a unified framework for code generation with pseudocode-based multi-task learning and reinforcement alignment"],"prefix":"10.1007","volume":"81","author":[{"given":"Yongjun","family":"Wen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhihao","family":"Cui","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yihao","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhao","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiake","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lijun","family":"Tang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,6,10]]},"reference":[{"key":"7487_CR1","unstructured":"Achiam J, Adler S, Agarwal S et\u00a0al (2023) Gpt-4 technical report. arXiv preprint arXiv: 2303.08774"},{"key":"7487_CR2","first-page":"1536","volume":"2020","author":"Z Feng","year":"2020","unstructured":"Feng Z, Guo D, Tang D et al (2020) Codebert: A pre-trained model for programming and natural languages. Findings of the Association for Computational Linguistics: EMNLP 2020:1536\u20131547","journal-title":"Findings of the Association for Computational Linguistics: EMNLP"},{"key":"7487_CR3","doi-asserted-by":"crossref","unstructured":"Wang Y, Wang W, Joty S et\u00a0al (2021) Codet5: Identifier-aware unified pre-trained encoder-decoder models for code understanding and generation. In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pp 8696\u20138708","DOI":"10.18653\/v1\/2021.emnlp-main.685"},{"issue":"6624","key":"7487_CR4","doi-asserted-by":"publisher","first-page":"1092","DOI":"10.1126\/science.abq1158","volume":"378","author":"Y Li","year":"2022","unstructured":"Li Y, Choi D, Chung J et al (2022) Competition-level code generation with alphacode. Science 378(6624):1092\u20131097","journal-title":"Science"},{"key":"7487_CR5","unstructured":"Chen M, Tworek J, Jun H et\u00a0al (2021) Evaluating large language models trained on code. arXiv preprint arXiv: 2107.03374"},{"key":"7487_CR6","unstructured":"Allal LB, Li R, Kocetkov D et\u00a0al (2023) Santacoder: don\u2019t reach for the stars! arXiv preprint arXiv:2301.03988"},{"key":"7487_CR7","unstructured":"Roziere B, Gehring J, Gloeckle F et\u00a0al (2023) Code llama: Open foundation models for code. arXiv preprint arXiv: 2308.12950"},{"issue":"2","key":"7487_CR8","first-page":"3","volume":"1","author":"EJ Hu","year":"2022","unstructured":"Hu EJ, Shen Y, Wallis P et al (2022) Lora: Low-rank adaptation of large language models. ICLR 1(2):3","journal-title":"ICLR"},{"key":"7487_CR9","first-page":"10088","volume":"36","author":"T Dettmers","year":"2023","unstructured":"Dettmers T, Pagnoni A, Holtzman A et al (2023) Qlora: Efficient finetuning of quantized llms. Adv Neural Inf Process Syst 36:10088\u201310115","journal-title":"Adv Neural Inf Process Syst"},{"key":"7487_CR10","first-page":"9459","volume":"33","author":"P Lewis","year":"2020","unstructured":"Lewis P, Perez E, Piktus A et al (2020) Retrieval-augmented generation for knowledge-intensive nlp tasks. Adv Neural Inf Process Syst 33:9459\u20139474","journal-title":"Adv Neural Inf Process Syst"},{"key":"7487_CR11","first-page":"24824","volume":"35","author":"J Wei","year":"2022","unstructured":"Wei J, Wang X, Schuurmans D et al (2022) Chain-of-thought prompting elicits reasoning in large language models. Adv Neural Inf Process Syst 35:24824\u201324837","journal-title":"Adv Neural Inf Process Syst"},{"issue":"2","key":"7487_CR12","first-page":"1","volume":"34","author":"J Li","year":"2025","unstructured":"Li J, Li G, Li Y et al (2025) Structured chain-of-thought prompting for code generation. ACM Transactions on Software Engineering and Methodology 34(2):1\u201323","journal-title":"ACM Transactions on Software Engineering and Methodology"},{"key":"7487_CR13","unstructured":"GLM T, Zeng A, Xu B et\u00a0al (2024) Chatglm: A family of large language models from glm-130b to glm-4 all tools. arXiv preprint arXiv: 2406.12793"},{"key":"7487_CR14","first-page":"124198","volume":"37","author":"Y Meng","year":"2025","unstructured":"Meng Y, Xia M, Chen D (2025) Simpo: Simple preference optimization with a reference-free reward. Adv Neural Inf Process Syst 37:124198\u2013124235","journal-title":"Adv Neural Inf Process Syst"},{"key":"7487_CR15","unstructured":"Bai J, Bai S, Chu Y et\u00a0al (2023) Qwen technical report. arXiv preprint arXiv: 2309.16609"},{"issue":"140","key":"7487_CR16","first-page":"1","volume":"21","author":"C Raffel","year":"2020","unstructured":"Raffel C, Shazeer N, Roberts A et al (2020) Exploring the limits of transfer learning with a unified text-to-text transformer. J Mach Learn Res 21(140):1\u201367","journal-title":"J Mach Learn Res"},{"key":"7487_CR17","unstructured":"Zheng L, Yuan J, Zhang Z et\u00a0al (2023) Self-infilling code generation. arXiv preprint arXiv: 2311.17972"},{"key":"7487_CR18","unstructured":"Hui B, Yang J, Cui Z et\u00a0al (2024) Qwen2. 5-coder technical report. arXiv preprint arXiv: 2409.12186"},{"key":"7487_CR19","unstructured":"Austin J, Odena A, Nye M et\u00a0al (2021) Program synthesis with large language models. arXiv preprint arXiv: 2108.07732"},{"key":"7487_CR20","unstructured":"Jain N, Han K, Gu A et\u00a0al (2024) Livecodebench: Holistic and contamination free evaluation of large language models for code. arXiv preprint arXiv: 2403.07974"},{"key":"7487_CR21","doi-asserted-by":"crossref","unstructured":"Donvir A, Panyam S, Paliwal G et\u00a0al (2024) The role of generative ai tools in application development: a comprehensive review of current technologies and practices. In: 2024 International Conference on Engineering Management of Communication and Technology (EMCTECH), IEEE, pp 1\u20139","DOI":"10.1109\/EMCTECH63049.2024.10741797"},{"key":"7487_CR22","unstructured":"Thoppilan R, De\u00a0Freitas D, Hall J et\u00a0al (2022) Lamda: Language models for dialog applications. arXiv preprint arXiv: 2201.08239"},{"key":"7487_CR23","unstructured":"Anil R, Dai AM, Firat O et\u00a0al (2023) Palm 2 technical report. arXiv preprint arXiv: 2305.10403"},{"key":"7487_CR24","unstructured":"Hurst A, Lerer A, Goucher AP et\u00a0al (2024) Gpt-4o system card. arXiv preprint arXiv: 2410.21276"},{"key":"7487_CR25","unstructured":"Christopoulou F, Lampouras G, Gritta M et\u00a0al (2022) Pangu-coder: Program synthesis with function-level language modeling. arXiv preprint arXiv: 2207.11280"},{"key":"7487_CR26","doi-asserted-by":"crossref","unstructured":"Zan D, Chen B, Yang D et\u00a0al (2022) Cert: continual pre-training on sketches for library-oriented code generation. arXiv preprint arXiv: 2206.06888","DOI":"10.24963\/ijcai.2022\/329"},{"key":"7487_CR27","unstructured":"Fried D, Aghajanyan A, Lin J et\u00a0al (2022) Incoder: a generative model for code infilling and synthesis. arXiv preprint arXiv: 2204.05999"},{"key":"7487_CR28","unstructured":"Li R, Allal LB, Zi Y et\u00a0al (2023) Starcoder: may the source be with you! arXiv preprint arXiv: 2305.06161"},{"key":"7487_CR29","unstructured":"Luo Z, Xu C, Zhao P et\u00a0al (2023) Wizardcoder: empowering code large language models with evol-instruct. arXiv preprint arXiv: 2306.08568"},{"key":"7487_CR30","doi-asserted-by":"crossref","unstructured":"Wang Y, Le H, Gotmare A et\u00a0al (2023) Codet5+: open code large language models for code understanding and generation. In: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pp 1069\u20131088","DOI":"10.18653\/v1\/2023.emnlp-main.68"},{"key":"7487_CR31","doi-asserted-by":"crossref","unstructured":"Liu B, Chen C, Gong Z et\u00a0al (2024) Mftcoder: boosting code llms with multitask fine-tuning. In: Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pp 5430\u20135441","DOI":"10.1145\/3637528.3671609"},{"key":"7487_CR32","unstructured":"Shen B, Zhang J, Chen T et\u00a0al (2023) Pangu-coder2: boosting large language models for code with ranking feedback. arXiv preprint arXiv: 2307.14936"},{"key":"7487_CR33","unstructured":"Xu C, Sun Q, Zheng K et\u00a0al (2024) Wizardlm: empowering large pre-trained language models to follow complex instructions. In: The Twelfth International Conference on Learning Representations"},{"key":"7487_CR34","first-page":"21314","volume":"35","author":"H Le","year":"2022","unstructured":"Le H, Wang Y, Gotmare AD et al (2022) Coderl: mastering code generation through pretrained models and deep reinforcement learning. Adv Neural Inf Process Syst 35:21314\u201321328","journal-title":"Adv Neural Inf Process Syst"},{"key":"7487_CR35","first-page":"9","volume":"2022","author":"X Wang","year":"2022","unstructured":"Wang X, Wang Y, Wan Y et al (2022) Compilable neural code generation with compiler feedback. Findings of the Association for Computational Linguistics: ACL 2022:9\u201319","journal-title":"Findings of the Association for Computational Linguistics: ACL"},{"key":"7487_CR36","unstructured":"Shojaee P, Jain A, Tipirneni S et\u00a0al (2023) Execution-based code generation using deep reinforcement learning. arXiv preprint arXiv: 2301.13816"},{"key":"7487_CR37","unstructured":"Schulman J, Wolski F, Dhariwal P et\u00a0al (2017) Proximal policy optimization algorithms. arXiv preprint arXiv: 1707.06347"},{"key":"7487_CR38","unstructured":"Liu J, Zhu Y, Xiao K et\u00a0al (2023) Rltf: reinforcement learning from unit test feedback. arXiv preprint arXiv: 2307.04349"},{"key":"7487_CR39","unstructured":"Guo D, Ren S, Lu S et\u00a0al (2020) Graphcodebert: pre-training code representations with data flow. arXiv preprint arXiv: 2009.08366"},{"key":"7487_CR40","unstructured":"Jiang X, Zheng Z, Lyu C et\u00a0al (2021) Treebert: a tree-based pre-trained model for programming language. In: Uncertainty in Artificial Intelligence, PMLR, pp 54\u201363"},{"key":"7487_CR41","first-page":"77942","volume":"36","author":"Y Zha","year":"2023","unstructured":"Zha Y, Yang Y, Li R et al (2023) Text alignment is an efficient unified model for massive nlp tasks. Adv Neural Inf Process Syst 36:77942\u201377968","journal-title":"Adv Neural Inf Process Syst"},{"key":"7487_CR42","first-page":"53728","volume":"36","author":"R Rafailov","year":"2023","unstructured":"Rafailov R, Sharma A, Mitchell E et al (2023) Direct preference optimization: Your language model is secretly a reward model. Adv Neural Inf Process Syst 36:53728\u201353741","journal-title":"Adv Neural Inf Process Syst"},{"key":"7487_CR43","doi-asserted-by":"publisher","DOI":"10.1145\/3715108","author":"R Mo","year":"2025","unstructured":"Mo R, Wang D, Zhan W et al (2025) Assessing and analyzing the correctness of github copilot\u2019s code suggestions. ACM Transactions on Software Engineering and Methodology. https:\/\/doi.org\/10.1145\/3715108","journal-title":"ACM Transactions on Software Engineering and Methodology"},{"key":"7487_CR44","unstructured":"Yeti\u015ftiren B, \u00d6zsoy I, Ayerdem M et\u00a0al (2023) Evaluating the code quality of ai-assisted code generation tools: an empirical study on github copilot, amazon codewhisperer, and chatgpt. arXiv preprint arXiv: 2304.10778"},{"key":"7487_CR45","unstructured":"Solovyeva L, Weidmann S, Castor F (2025) Ai-powered, but power-hungry? energy efficiency of llm-generated code. arXiv preprint arXiv: 2502.02412"},{"key":"7487_CR46","unstructured":"Vaswani A, Shazeer N, Parmar N et\u00a0al (2017) Attention is all you need. Advances in neural information processing systems 30"},{"key":"7487_CR47","unstructured":"Dubey A, Jauhri A, Pandey A et\u00a0al (2024) The llama 3 herd of models. arXiv preprint arXiv: 2407.21783"},{"key":"7487_CR48","doi-asserted-by":"crossref","unstructured":"Gong Z, Yu H, Liao C et\u00a0al (2024) Coba: convergence balancer for multitask finetuning of large language models. In: Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pp 8063\u20138077","DOI":"10.18653\/v1\/2024.emnlp-main.459"},{"key":"7487_CR49","first-page":"21558","volume":"36","author":"J Liu","year":"2023","unstructured":"Liu J, Xia CS, Wang Y et al (2023) Is your code generated by chatgpt really correct? rigorous evaluation of large language models for code generation. Adv Neural Inf Process Syst 36:21558\u201321572","journal-title":"Adv Neural Inf Process Syst"},{"key":"7487_CR50","doi-asserted-by":"crossref","unstructured":"Kwon W, Li Z, Zhuang S et\u00a0al (2023) Efficient memory management for large language model serving with pagedattention. In: Proceedings of the 29th Symposium on Operating Systems Principles, pp 611\u2013626","DOI":"10.1145\/3600006.3613165"},{"key":"7487_CR51","unstructured":"Yang A, Yang B, Hui B et\u00a0al (2024) Qwen2 technical report. arXiv preprint arXiv: 2407.10671"},{"key":"7487_CR52","unstructured":"Jiang AQ, Sablayrolles A, Mensch A et\u00a0al (2023) Mistral 7b. arXiv preprint arXiv: 2310.06825"},{"key":"7487_CR53","unstructured":"Mistral AI Team (2024) Un ministral, des ministraux. mistral Research Licensehttps:\/\/mistral.ai\/fr\/news\/ministraux\/,"},{"key":"7487_CR54","unstructured":"Zhu Q, Guo D, Shao Z et\u00a0al (2024) Deepseek-coder-v2: breaking the barrier of closed-source models in code intelligence. arXiv preprint arXiv: 2406.11931"},{"key":"7487_CR55","unstructured":"Liu A, Feng B, Xue B et\u00a0al (2024) Deepseek-v3 technical report. arXiv preprint arXiv: 2412.19437"},{"key":"7487_CR56","doi-asserted-by":"crossref","unstructured":"Rasley J, Rajbhandari S, Ruwase O et\u00a0al (2020) Deepspeed: system optimizations enable training deep learning models with over 100 billion parameters. In: Proceedings of the 26th ACM SIGKDD international conference on knowledge discovery & data mining, pp 3505\u20133506","DOI":"10.1145\/3394486.3406703"},{"key":"7487_CR57","doi-asserted-by":"crossref","unstructured":"Rajbhandari S, Rasley J, Ruwase O et al (2020) Zero: memory optimizations toward training trillion parameter models. SC20: International Conference for High Performance Computing. Networking, Storage and Analysis, IEEE, pp 1\u201316","DOI":"10.1109\/SC41405.2020.00024"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-025-07487-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11227-025-07487-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-025-07487-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,10]],"date-time":"2025-06-10T15:55:36Z","timestamp":1749570936000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11227-025-07487-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,10]]},"references-count":57,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2025,6]]}},"alternative-id":["7487"],"URL":"https:\/\/doi.org\/10.1007\/s11227-025-07487-1","relation":{},"ISSN":["1573-0484"],"issn-type":[{"value":"1573-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,10]]},"assertion":[{"value":"20 May 2025","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 June 2025","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"1010"}}