UNICS: Multilingual Code Search via Unified Pseudocode and Contrastive Transfer Learning
Proceedings of the ACM on Software Engineering · 30.06.2026 · 3 (FSE) · 92-115
DOI: 10.1145/3797067 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the ACM on Software Engineering, online erschienen am 30.06.2026. Verfasst von Ye Fan und 4 weiteren Autor:innen. Die Arbeit nennt 63 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China Grants, The 6th \"333 Project\" Leading Talent Team Project of Jiangsu Province.
Abstract (Originalsprache)
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.
Förderung
- National Natural Science Foundation of China Grants
- The 6th \"333 Project\" Leading Talent Team Project of Jiangsu Province
Zitieren
APA
Fan, Y., Ge, J., Li, C., Huang, L., & Luo, B. (2026). UNICS: Multilingual Code Search via Unified Pseudocode and Contrastive Transfer Learning. Proceedings of the ACM on Software Engineering, 3(FSE), 92-115. https://doi.org/10.1145/3797067
Vancouver
Fan Y, Ge J, Li C, Huang L, Luo B. UNICS: Multilingual Code Search via Unified Pseudocode and Contrastive Transfer Learning. Proceedings of the ACM on Software Engineering. 2026;3(FSE):92-115. doi:10.1145/3797067
BibTeX
@article{Fan2026,
author = {Fan, Ye and Ge, Jidong and Li, Chuanyi and Huang, LiGuo and Luo, Bin},
title = {UNICS: Multilingual Code Search via Unified Pseudocode and Contrastive Transfer Learning},
journal = {Proceedings of the ACM on Software Engineering},
year = {2026},
volume = {3},
number = {FSE},
pages = {92--115},
doi = {10.1145/3797067}
}
EUVIMED