{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T19:03:47Z","timestamp":1782846227668,"version":"3.54.5"},"reference-count":63,"publisher":"Association for Computing Machinery (ACM)","issue":"FSE","license":[{"start":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T00:00:00Z","timestamp":1782777600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China Grants","doi-asserted-by":"crossref","award":["92582204"],"award-info":[{"award-number":["92582204"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"The 6th \\\"333 Project\\\" Leading Talent Team Project of Jiangsu Province","award":["333"],"award-info":[{"award-number":["333"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Proc. ACM Softw. Eng."],"published-print":{"date-parts":[[2026,6,30]]},"abstract":"<jats:p>While pre-trained models have achieved remarkable success in code search, their multilingual capabilities remain a major hurdle, plagued by data imbalance, cross-lingual semantic interference, and the loss of critical information from existing unified representations like Abstract Syntax Trees (ASTs) or Intermediate Representations (IRs). Furthermore, conventional contrastive learning strategies often rely on simplistic hard negative sampling while overlooking the potential of mining hard positives to learn code's intrinsic semantic invariance. To address these challenges, we introduce UNICS, a framework for multilingual code search built on a two-stage training strategy. In the first stage, UNICS is pre-trained on a novel dataset we constructed, which uses pseudo-code as a unified representation to learn a cross-lingual, algorithm-level logic that preserves full semantic fidelity. The second stage employs a multi-task transfer learning strategy that adapts this general knowledge to specific languages by decomposing code into semantic slices (e.g., API calls, function bodies) and incorporating tasks for hard positive mining and cross-lingual dynamic hard negative sampling. Experimental results demonstrate that UNICS achieves state-of-the-art performance across multiple multilingual and cross-lingual benchmarks, showcasing superior generalization and performance balance, especially in zero-shot transfer tasks to low-resource languages.<\/jats:p>","DOI":"10.1145\/3797067","type":"journal-article","created":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T17:06:14Z","timestamp":1782839174000},"page":"92-115","source":"Crossref","is-referenced-by-count":0,"title":["UNICS: Multilingual Code Search via Unified Pseudocode and Contrastive Transfer Learning"],"prefix":"10.1145","volume":"3","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3584-9920","authenticated-orcid":false,"given":"Ye","family":"Fan","sequence":"first","affiliation":[{"name":"Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1773-0942","authenticated-orcid":false,"given":"Jidong","family":"Ge","sequence":"additional","affiliation":[{"name":"Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9270-5072","authenticated-orcid":false,"given":"Chuanyi","family":"Li","sequence":"additional","affiliation":[{"name":"Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7790-0195","authenticated-orcid":false,"given":"LiGuo","family":"Huang","sequence":"additional","affiliation":[{"name":"Southern Methodist University, Dallas, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-1102-9584","authenticated-orcid":false,"given":"Bin","family":"Luo","sequence":"additional","affiliation":[{"name":"Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,30]]},"reference":[{"key":"e_1_2_1_1_1","unstructured":"2023. Github Website. https:\/\/www.github.com."},{"key":"e_1_2_1_2_1","unstructured":"2026. Code Embedding. https:\/\/bitbucket.org\/anonymous_code\/code_embedding."},{"key":"e_1_2_1_3_1","doi-asserted-by":"publisher","unstructured":"Shushan Arakelyan Anna Hakhverdyan Miltiadis Allamanis Luis Garcia Christophe Hauser and Xiang Ren. 2022. NS3: Neuro-symbolic Semantic Code Search. (2022). doi:10.52202\/068431-0761 10.52202\/068431-0761","DOI":"10.52202\/068431-0761"},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/1753326.1753402"},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/1518701.1518944"},{"key":"e_1_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462840"},{"key":"e_1_2_1_7_1","volume-title":"ECAI 2012-20th European Conference on Artificial Intelligence: Preference Learning: Problems and Applications in AI Workshop","volume":"242","author":"Busa-Fekete R\u00f3bert","year":"2012","unstructured":"R\u00f3bert Busa-Fekete, Gy\u00f6rgy Szarvas, Tam\u00e1s Elteto, and Bal\u00e1zs K\u00e9gl. 2012. An apple-to-apple comparison of learningto-rank algorithms in terms of normalized discounted cumulative gain. In ECAI 2012-20th European Conference on Artificial Intelligence: Preference Learning: Problems and Applications in AI Workshop, Vol. 242. Ios Press."},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3338906.3340458"},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSME.2017.56"},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3510003.3510125"},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/2393596.2393606"},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2402.03216"},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/317"},{"key":"e_1_2_1_14_1","volume-title":"Scotch: A Semantic Code Search Engine for IDEs. In Deep Learning for Code Workshop. https:\/\/openreview.net\/forum?id=rSxfCiOZk-c","author":"Dahal Samip","year":"2022","unstructured":"Samip Dahal, Adyasha Maharana, and Mohit Bansal. 2022. Scotch: A Semantic Code Search Engine for IDEs. In Deep Learning for Code Workshop. https:\/\/openreview.net\/forum?id=rSxfCiOZk-c"},{"key":"e_1_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2009.03376"},{"key":"e_1_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2005.12766"},{"key":"e_1_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/2020.FINDINGS-EMNLP.139"},{"key":"e_1_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/2021.EMNLP-"},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3180155.3180167"},{"key":"e_1_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/2022.ACL-LONG.499"},{"key":"e_1_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2009.08366"},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","unstructured":"Dan Hendrycks Steven Basart Saurav Kadavath Mantas Mazeika Akul Arora Ethan Guo Collin Burns Samir Puranik Horace He Dawn Song et al. 2021. Measuring coding challenge competence with apps. arXiv preprint arXiv:2105.09938 (2021). doi:10.48550\/arXiv.2105.09938 10.48550\/arXiv.2105.09938","DOI":"10.48550\/arXiv.2105.09938"},{"key":"e_1_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSM.2009.5306387"},{"key":"e_1_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/2021.ACL-LONG.442"},{"key":"e_1_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3609437.3609439"},{"key":"e_1_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1909.09436"},{"key":"e_1_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2112.09118"},{"key":"e_1_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/2021.EMNLP-MAIN.482"},{"key":"e_1_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/2020"},{"key":"e_1_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/2568225.2568292"},{"key":"e_1_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i8.28713"},{"key":"e_1_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2201.10866"},{"key":"e_1_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/2950290.2950341"},{"key":"e_1_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1007\/S10618-008-0118-X"},{"key":"e_1_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.04664"},{"key":"e_1_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASE.2015.42"},{"key":"e_1_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/2021.FINDINGS-ACL.51"},{"key":"e_1_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/SANER56733.2023.00021"},{"key":"e_1_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSE"},{"key":"e_1_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/1985793.1985809"},{"key":"e_1_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2201.10005"},{"key":"e_1_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.24963\/IJCAI.2022\/775"},{"key":"e_1_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/2597073.2597077"},{"key":"e_1_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3211346.3211353"},{"key":"e_1_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2204.03293"},{"key":"e_1_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE48619.2023"},{"key":"e_1_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3387904.3389269"},{"key":"e_1_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSME.2014.77"},{"key":"e_1_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3368089.3417058"},{"key":"e_1_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASE.2019.00012"},{"key":"e_1_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/SANER48275.2020.9054857"},{"key":"e_1_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2108.04556"},{"key":"e_1_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1304.6480"},{"key":"e_1_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/2021.EMNLP-MAIN.685"},{"key":"e_1_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2110.02027"},{"key":"e_1_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095319"},{"key":"e_1_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/SANER48275.2020.9054840"},{"key":"e_1_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2310.04951"},{"key":"e_1_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1145\/2950290.2983955"},{"key":"e_1_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1805.07836"},{"key":"e_1_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2402.14658"},{"key":"e_1_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1145\/2950290.2950298"},{"key":"e_1_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2206.08474"}],"container-title":["Proceedings of the ACM on Software Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3797067","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T18:08:27Z","timestamp":1782842907000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3797067"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,30]]},"references-count":63,"journal-issue":{"issue":"FSE","published-print":{"date-parts":[[2026,6,30]]}},"alternative-id":["10.1145\/3797067"],"URL":"https:\/\/doi.org\/10.1145\/3797067","relation":{},"ISSN":["2994-970X"],"issn-type":[{"value":"2994-970X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,30]]}}}