@inproceedings{zhou-etal-2026-team,
    title = "Team {HITS} at {S}em{E}val-2026 Task 4:Enhancing narrative text embedding model training with hard negatives generation and self-distillation",
    author = "Zhou, Qian  and
      Fan, Yi  and
      Liu, Wei  and
      Strube, Michael",
    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/acl-awards/2026.semeval-1.338/",
    doi = "10.18653/v1/2026.semeval-1.338",
    pages = "2679--2688",
    ISBN = "979-8-89176-414-9",
    abstract = "Narrative text embedding is the basis for machines to understand and represent stories. However, it is challenging because it depends on similarities in theme, course of action, and outcomes. To target this challenge, we present a task-aligned system for SemEval-2026 Task 4 Track B. We first use Qwen2.5-32B-Instruct model to generate hard negatives from three narrative dimensions. We then train a Qwen3-Embedding-8B model with a multi-negative contrastive objective and use a teacher model that has the same architecture as the training model. The model achieves the best result in the current training phase by introducing ``soft label'' via KL Divergence."
}