@inproceedings{guo-etal-2026-narrative,
    title = "Narrative Nexus at {S}em{E}val-2026 Task 4: Modeling Narrative Similarity via Instruction-Based Fine-Tuning and Synthetic Data Augmentation",
    author = "Guo, Haotan  and
      Na, Hongbin  and
      Wang, Zimu  and
      Wang, Wei",
    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-1.352/",
    pages = "2793--2799",
    ISBN = "979-8-89176-414-9",
    abstract = "Narrative similarity assessment requires models to reason beyond surface-level lexical overlap and capture higher-level plot structures and thematic relationships. In this paper, we address SemEval-2026 Task 4 Track A: Narrative Story Similarity by reformulating it as an instruction-following generation problem. We employ parameter-efficient fine-tuning via LoRA to adapt pretrained large language models for triplet-based narrative comparison. To overcome the limitations imposed by the scarcity of human-annotated data, we further incorporate synthetic triplet samples generated by a large language model for data augmentation. Experimental results demonstrate that our fine-tuned Qwen2.5-7B model achieves competitive performance, outperforming the zero-shot GPT-4o-mini baseline. These findings underscore the effectiveness of task-specific adaptation combined with synthetic data augmentation for narrative similarity modeling."
}