{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T23:51:40Z","timestamp":1770335500582,"version":"3.49.0"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,12,16]],"date-time":"2025-12-16T00:00:00Z","timestamp":1765843200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,12,16]],"date-time":"2025-12-16T00:00:00Z","timestamp":1765843200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"the Key Program of the National Natural Science Foundation of China","award":["U224120044"],"award-info":[{"award-number":["U224120044"]}]},{"DOI":"10.13039\/501100001809","name":"the Joint Funds of the National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["U2241216"],"award-info":[{"award-number":["U2241216"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"the National Science and Technology Major Project of China","award":["No. Y2022-V-0001-0027"],"award-info":[{"award-number":["No. Y2022-V-0001-0027"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["World Wide Web"],"published-print":{"date-parts":[[2026,2]]},"DOI":"10.1007\/s11280-025-01395-3","type":"journal-article","created":{"date-parts":[[2025,12,16]],"date-time":"2025-12-16T07:59:45Z","timestamp":1765871985000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["P2N2S: Bridging the gap between natural and programming languages for code summarization via large language models"],"prefix":"10.1007","volume":"29","author":[{"given":"Yijia","family":"Tang","sequence":"first","affiliation":[]},{"given":"YaoShen","family":"Yu","sequence":"additional","affiliation":[]},{"given":"Zhiqiu","family":"Huang","sequence":"additional","affiliation":[]},{"given":"Bowei","family":"Xia","sequence":"additional","affiliation":[]},{"given":"Yukun","family":"Cao","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,12,16]]},"reference":[{"key":"1395_CR1","doi-asserted-by":"publisher","unstructured":"Iyer, S., Konstas, I., Cheung, A., Zettlemoyer, L.: Summarizing source code using a neural attention model. In: Erk, K., Smith, N.A. (eds.) Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 2073\u20132083. Association for Computational Linguistics, Berlin, Germany (2016). https:\/\/doi.org\/10.18653\/v1\/P16-1195. https:\/\/aclanthology.org\/P16-1195\/","DOI":"10.18653\/v1\/P16-1195"},{"key":"1395_CR2","doi-asserted-by":"publisher","unstructured":"LeClair, A., Jiang, S., McMillan, C.: A neural model for generating natural language summaries of program subroutines. In: Proceedings of the 41st International Conference on Software Engineering. ICSE \u201919, pp. 795\u2013806. IEEE Press, (2019). https:\/\/doi.org\/10.1109\/ICSE.2019.00087 . https:\/\/doi.org\/10.1109\/ICSE.2019.00087","DOI":"10.1109\/ICSE.2019.00087"},{"key":"1395_CR3","doi-asserted-by":"crossref","unstructured":"Hu, X., Li, G., Xia, X., Lo, D., Jin, Z.: Deep code comment generation. In: Proceedings of the 26th Conference on Program Comprehension, pp. 200\u2013210 (2018)","DOI":"10.1145\/3196321.3196334"},{"issue":"6","key":"1395_CR4","first-page":"3472","volume":"49","author":"C Shi","year":"2023","unstructured":"Shi, C., Cai, B., Zhao, Y., Gao, L., Sood, K., Xiang, Y.: Coss: Leveraging statement semantics for code summarization. IEEE Trans. Software Eng. 49(6), 3472\u20133486 (2023)","journal-title":"IEEE Trans. Software Eng."},{"key":"1395_CR5","doi-asserted-by":"crossref","unstructured":"Zhang, J., Wang, X., Zhang, H., Sun, H., Wang, K., Liu, X.: A novel neural source code representation based on abstract syntax tree. In: 2019 IEEE\/ACM 41st International Conference on Software Engineering (ICSE), pp. 783\u2013794 (2019). IEEE","DOI":"10.1109\/ICSE.2019.00086"},{"key":"1395_CR6","unstructured":"Haldar, R., Hockenmaier, J.: Analyzing the performance of large language models on code summarization. In: Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pp. 995\u20131008 (2024)"},{"key":"1395_CR7","unstructured":"Achiam, J., Adler, S., Agarwal, S., Ahmad, L., Akkaya, I., Aleman, F.L., Almeida, D., Altenschmidt, J., Altman, S., Anadkat, S., et al.: Gpt-4 technical report, (2023). arXiv preprint arXiv:2303.08774"},{"key":"1395_CR8","unstructured":"Grattafiori, A., Dubey, A., Jauhri, A., Pandey, A., Kadian, A., Al-Dahle, A., Letman, A., Mathur, A., Schelten, A., Vaughan, A., et al.: The llama 3 herd of models, (2024). arXiv preprint arXiv:2407.21783"},{"key":"1395_CR9","unstructured":"Guo, D., Yang, D., Zhang, H., Song, J., Zhang, R., Xu, R., Zhu, Q., Ma, S., Wang, P., Bi, X., et al.: Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning, (2025). arXiv preprint arXiv:2501.12948"},{"key":"1395_CR10","doi-asserted-by":"publisher","unstructured":"Ahmed, T., Pai, K.S., Devanbu, P., Barr, E.: Automatic semantic augmentation of language model prompts (for code summarization). In: Proceedings of the IEEE\/ACM 46th International Conference on Software Engineering. ICSE \u201924. Association for Computing Machinery, New York, NY, USA (2024). https:\/\/doi.org\/10.1145\/3597503.3639183 . https:\/\/doi.org\/10.1145\/3597503.3639183","DOI":"10.1145\/3597503.3639183"},{"key":"1395_CR11","doi-asserted-by":"publisher","unstructured":"Lomshakov, V., Podivilov, A., Savin, S., Baryshnikov, O., Lisevych, A., Nikolenko, S.: ProConSuL: Project context for code summarization with LLMs. In: Dernoncourt, F., Preo\u0163iuc-Pietro, D., Shimorina, A. (eds.) Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: Industry Track, pp. 866\u2013880. Association for Computational Linguistics, Miami, Florida, US (2024). https:\/\/doi.org\/10.18653\/v1\/2024.emnlp-industry.65. https:\/\/aclanthology.org\/2024.emnlp-industry.65\/","DOI":"10.18653\/v1\/2024.emnlp-industry.65"},{"key":"1395_CR12","unstructured":"Sun, W., Zhang, Y., Zhu, J., Wang, Z., Fang, C., Zhang, Y., Feng, Y., Huang, J., Wang, X., Jin, Z., et al.: Commenting higher-level code unit: Full code, reduced code, or hierarchical code summarization, (2025). arXiv preprint arXiv:2503.10737"},{"key":"1395_CR13","doi-asserted-by":"crossref","unstructured":"Iyer, S., Konstas, I., Cheung, A., Zettlemoyer, L.: Summarizing source code using a neural attention model. In: 54th Annual Meeting of the Association for Computational Linguistics 2016, pp. 2073\u20132083 (2016). Association for Computational Linguistics","DOI":"10.18653\/v1\/P16-1195"},{"key":"1395_CR14","unstructured":"Alon, U., Brody, S., Levy, O., Yahav, E.: code2seq: Generating sequences from structured representations of code. In: International Conference on Learning Representations"},{"key":"1395_CR15","doi-asserted-by":"crossref","unstructured":"Feng, Z., Guo, D., Tang, D., Duan, N., Feng, X., Gong, M., Shou, L., Qin, B., Liu, T., Jiang, D., et al.: Codebert: A pre-trained model for programming and natural languages, (2020). arXiv preprint arXiv:2002.08155","DOI":"10.18653\/v1\/2020.findings-emnlp.139"},{"key":"1395_CR16","doi-asserted-by":"crossref","unstructured":"Wang, Y., Wang, W., Joty, S., Hoi, S.C.: 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 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.685"},{"key":"1395_CR17","doi-asserted-by":"crossref","unstructured":"Ahmad, W., Chakraborty, S., Ray, B., Chang, K.-W.: Unified pre-training for program understanding and generation. In: Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 2655\u20132668 (2021)","DOI":"10.18653\/v1\/2021.naacl-main.211"},{"key":"1395_CR18","unstructured":"Guo, D., Ren, S., Lu, S., Feng, Z., Tang, D., LIU, S., Zhou, L., Duan, N., Svyatkovskiy, A., Fu, S., et al.: Graphcodebert: Pre-training code representations with data flow. In: International Conference on Learning Representations"},{"key":"1395_CR19","doi-asserted-by":"publisher","unstructured":"Guo, D., Lu, S., Duan, N., Wang, Y., Zhou, M., Yin, J.: UniXcoder: Unified cross-modal pre-training for code representation. In: Muresan, S., Nakov, P., Villavicencio, A. (eds.) Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 7212\u20137225. Association for Computational Linguistics, Dublin, Ireland (2022).https:\/\/doi.org\/10.18653\/v1\/2022.acl-long.499. https:\/\/aclanthology.org\/2022.acl-long.499\/","DOI":"10.18653\/v1\/2022.acl-long.499"},{"key":"1395_CR20","doi-asserted-by":"publisher","unstructured":"Allamanis, M., Barr, E.T., Devanbu, P., Sutton, C.: A survey of machine learning for big code and naturalness. ACM Comput. Surv. 51(4) (2018). https:\/\/doi.org\/10.1145\/3212695","DOI":"10.1145\/3212695"},{"key":"1395_CR21","doi-asserted-by":"publisher","unstructured":"Wang, Y., Liu, J., Li, G., Jin, Z.: Demystifying neural code intelligence models through structural pruning. In: Proceedings of the 45th International Conference on Software Engineering (ICSE), pp. 2014\u20132026. IEEE\/ACM, (2023). https:\/\/doi.org\/10.1109\/ICSE48619.2023.00167","DOI":"10.1109\/ICSE48619.2023.00167"},{"key":"1395_CR22","unstructured":"Chen, M., Tworek, J., Jun, H., Yuan, Q., Oliveira\u00a0Pinto, H.P., Kaplan, J., Edwards, H., Burda, Y., Joseph, N., Brockman, G., Ray, A., Puri, G.i.S., Mishkin, P., Chan, B., Gray, S., Ryder, N., Pavlov, M., Power, A., Kaiser, L., Bavarian, M., Winter, C., Tillet, P., Such, F.P., Cummings, D., Plappert, M., Chantzis, F., Barnes, E., Herbert-Voss, A., Guss, W., Nichol, A., Paino, C., Tezak, N., Tang, J., Babuschkin, I., Balaji, S., Jain, S., Saunders, W., Hesse, C., Carr, A., Leike, J., Achiam, J., Misra, V., Morikawa, E., Radford, A., Knight, M., Brundage, M., Murati, M., Mayer, K., Welinder, P., McGrew, B., Amodei, D., Sutskever, I., Zaremba, W.: Evaluating large language models trained on code, (2021). arXiv preprint arXiv:2107.03374"},{"key":"1395_CR23","first-page":"3843","volume":"35","author":"A Lewkowycz","year":"2022","unstructured":"Lewkowycz, A., Andreassen, A., Dohan, D., Dyer, E., Michalewski, H., Ramasesh, V., Slone, A., Anil, C., Schlag, I., Gutman-Solo, T., et al.: Solving quantitative reasoning problems with language models. Adv. Neural. Inf. Process. Syst. 35, 3843\u20133857 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"1395_CR24","doi-asserted-by":"crossref","unstructured":"Yang, Z., Chen, S., Gao, C., Li, Z., Hu, X., Liu, K., Xia, X.: An empirical study of retrieval-augmented code generation: Challenges and opportunities. ACM Trans Soft Eng Methodol (2025)","DOI":"10.1145\/3717061"},{"issue":"6","key":"1395_CR25","doi-asserted-by":"publisher","first-page":"162","DOI":"10.1007\/s10664-024-10553-6","volume":"29","author":"X Zhang","year":"2024","unstructured":"Zhang, X., Hou, X., Qiao, X., Song, W.: A review of automatic source code summarization. Empir. Softw. Eng. 29(6), 162 (2024)","journal-title":"Empir. Softw. Eng."},{"key":"1395_CR26","doi-asserted-by":"crossref","unstructured":"Lomshakov, V., Podivilov, A., Savin, S., Baryshnikov, O., Lisevych, A., Nikolenko, S.: Proconsul: Project context for code summarization with llms. In: Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: Industry Track, pp. 866\u2013880 (2024)","DOI":"10.18653\/v1\/2024.emnlp-industry.65"},{"key":"1395_CR27","doi-asserted-by":"crossref","unstructured":"Hu, X., Li, G., Xia, X., Lo, D., Lu, S., Jin, Z.: Summarizing source code with transferred api knowledge. In: Proceedings of the 27th International Joint Conference on Artificial Intelligence. IJCAI\u201918, pp. 2269\u20132275. AAAI Press, (2018)","DOI":"10.24963\/ijcai.2018\/314"},{"key":"1395_CR28","unstructured":"Husain, H., Wu, H.-H., Gazit, T., Allamanis, M., Brockschmidt, M.: Codesearchnet challenge: Evaluating the state of semantic code search, (2019). arXiv preprint arXiv:1909.09436"},{"key":"1395_CR29","doi-asserted-by":"crossref","unstructured":"Guo, J., Liu, J., Liu, X., Li, L.: Summarizing source code through heterogeneous feature fusion and extraction. Inform. Fusion 103, 102058 (2024)","DOI":"10.1016\/j.inffus.2023.102058"},{"key":"1395_CR30","doi-asserted-by":"crossref","unstructured":"Zhang, J., Wang, X., Zhang, H., Sun, H., Liu, X.: Retrieval-based neural source code summarization. In: Proceedings of the ACM\/IEEE 42nd International Conference on Software Engineering, pp. 1385\u20131397 (2020)","DOI":"10.1145\/3377811.3380383"},{"key":"1395_CR31","doi-asserted-by":"crossref","unstructured":"Tang, Z., Shen, X., Li, C., Ge, J., Huang, L., Zhu, Z., Luo, B.: Ast-trans: Code summarization with efficient tree-structured attention. In: Proceedings of the 44th International Conference on Software Engineering, pp. 150\u2013162 (2022)","DOI":"10.1145\/3510003.3510224"},{"key":"1395_CR32","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.-J.: Bleu: a method for automatic evaluation of machine translation. In: Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, pp. 311\u2013318 (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"1395_CR33","unstructured":"Banerjee, S., Lavie, A.: Meteor: An automatic metric for mt evaluation with improved correlation with human judgments. In: Proceedings of the Acl Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation And\/or Summarization, pp. 65\u201372 (2005)"},{"key":"1395_CR34","unstructured":"Lin, C.-Y.: Rouge: A package for automatic evaluation of summaries. In: Text Summarization Branches Out, pp. 74\u201381 (2004)"},{"key":"1395_CR35","doi-asserted-by":"crossref","unstructured":"Vedantam, R., Lawrence\u00a0Zitnick, C., Parikh, D.: Cider: Consensus-based image description evaluation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4566\u20134575 (2015)","DOI":"10.1109\/CVPR.2015.7299087"},{"issue":"6","key":"1395_CR36","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1007\/s10664-023-10378-9","volume":"28","author":"E Shi","year":"2023","unstructured":"Shi, E., Wang, Y., Du, L., Zhang, H., Han, S., Zhang, D., Sun, H.: Cocoast: representing source code via hierarchical splitting and reconstruction of abstract syntax trees. Empir. Softw. Eng. 28(6), 135 (2023)","journal-title":"Empir. Softw. Eng."},{"key":"1395_CR37","doi-asserted-by":"crossref","unstructured":"Lewis, M., Liu, Y., Goyal, N., Ghazvininejad, M., Mohamed, A., Levy, O., Stoyanov, V., Zettlemoyer, L.: Bart: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension, (2019). arXiv preprint arXiv:1910.13461","DOI":"10.18653\/v1\/2020.acl-main.703"},{"issue":"140","key":"1395_CR38","first-page":"1","volume":"21","author":"C Raffel","year":"2020","unstructured":"Raffel, C., Shazeer, N., Roberts, A., Lee, K., Narang, S., Matena, M., Zhou, Y., Li, W., Liu, P.J.: Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res. 21(140), 1\u201367 (2020)","journal-title":"J. Mach. Learn. Res."},{"key":"1395_CR39","unstructured":"Yan, Y., Qi, W., Gong, Y., Liu, D., Duan, N., Chen, J., Zhang, R., Zhou, M.: Prophetnet: Predicting future n-gram for sequence-to-sequence pre-training, (2020). arXiv preprint arXiv:2001.04063"},{"key":"1395_CR40","unstructured":"Zhang, J., Zhao, Y., Saleh, M., Liu, P.J.: PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization (2019)"},{"key":"1395_CR41","unstructured":"Zaheer, M., Guruganesh, G., Dubey, A., Ainslie, J., Alberti, C., Ontanon, S., Pham, P., Ravula, A., Wang, Q., Yang, L., Ahmed, A.: Big Bird: Transformers for Longer Sequences (2021)"}],"container-title":["World Wide Web"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11280-025-01395-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11280-025-01395-3","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11280-025-01395-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T11:21:10Z","timestamp":1770290470000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11280-025-01395-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,16]]},"references-count":41,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,2]]}},"alternative-id":["1395"],"URL":"https:\/\/doi.org\/10.1007\/s11280-025-01395-3","relation":{},"ISSN":["1386-145X","1573-1413"],"issn-type":[{"value":"1386-145X","type":"print"},{"value":"1573-1413","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,16]]},"assertion":[{"value":"27 September 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 November 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 December 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 December 2025","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no Conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflicts of interest"}},{"value":"The authors declare no competing interests.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"7"}}