@inproceedings{li-2026-srcb,
    title = "{SRCB} at {S}em{E}val-2026 Task 3: Boosting {D}im{ASR} via Contrastive {LLM}-Based Data Augmentation",
    author = "Li, Hongyu",
    editor = "Kochmar, Ekaterina  and
      Ghosh, Debanjan  and
      North, Kai  and
      Komachi, Mamoru",
    booktitle = "Proceedings of the 20th {I}nternational {W}orkshop on {S}emantic {E}valuation (2026)",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.semeval-1.42/",
    pages = "290--294",
    ISBN = "979-8-89176-414-9",
    abstract = "We present our system for the DimASR subtask of SemEval-2026 Task 3: DimABSA, targeting dimensional sentiment regression of Valence-Arousal scores in English restaurant reviews. Our approach leverages Qwen3 large language models combined with contrastive LLM-based data augmentation to enrich training data and capture subtle affective variations. Experiments show that this data augmentation framework significantly improves performance on the DimASR task, particularly in capturing subtle affective shifts at the aspect level. Finally, our system achieves a score of 1.227 RMSE on the test set."
}