@inproceedings{fan-etal-2025-ctyun,
    title = "{CTYUN}-{AI} at {S}em{E}val-2025 Task 1: Learning to Rank for Idiomatic Expressions",
    author = "Fan, Yuming  and
      Yang, Dongming  and
      Cai, Zefeng  and
      Lin, Binghuai",
    editor = "Rosenthal, Sara  and
      Ros{\'a}, Aiala  and
      Ghosh, Debanjan  and
      Zampieri, Marcos",
    booktitle = "Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/corrections-2025-08/2025.semeval-1.3/",
    pages = "16--19",
    ISBN = "979-8-89176-273-2",
    abstract = "We propose a multimodal framework integrating textual context and image caption analysis via systematic data augmentation and parameter-efficient fine-tuning. Our approach features: (1) option shuffling to eliminate positional bias, (2) lexical augmentation through synonym replacement and back-translation, and (3) optimized cross-modal ranking adaptation. The system ranks first in Portuguese (Top-1 Acc: 0.92) and second in English (Top-1 Acc: 0.87) on CodaBench. Experiments across 7B-72B models reveal 32B architectures achieve optimal capacity-trainability balance, while larger 72B models suffer from overfitting. Results demonstrate the limitations of GPT-4 knowledge distillation and emphasize controlled data augmentation for idiomatic language learning, advancing multimodal figurative language processing techniques."
}