@inproceedings{colli-etal-2026-tfb,
    title = "{TFB} at {S}em{E}val-2026 Task 4: Diagnosing Model Failures in Narrative Understanding",
    author = "Colli, Anna  and
      Rachmat, Benedictus Kent  and
      Sauvage, Eve  and
      Battistelli, Delphine  and
      Gerald, Thomas  and
      Grouin, Cyril  and
      Tourille, Julien  and
      Zhang, Zheng",
    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-1.367/",
    pages = "2932--2938",
    ISBN = "979-8-89176-414-9",
    abstract = "We describe the participation of team TFB in SemEval-2026 Task 4 on narrative similarity. We explore ColBERT-inspired sentence-level late interaction to capture event reordering, compare fine-tuning with synthetic data at multiple difficulty tiers, finding that distribution proximity to the target data matters more than volume and evaluate chain-of-thought prompting. We complement our approaches with a human annotation study (Krippendorff{'}s alpha=0.32) confirming the task{'}s inherent difficulty, an analysis of synthetic data distribution shift explaining why fine-tuning on out-of-distribution data hurts the model{'}s performance. Despite our tests, we didn{'}t surpass results of sentence-t5-xxl on Track B and Qwen2.5-7B on Track A. We finally decided to submit these two models for the task."
}