@inproceedings{chi-hsieh-2025-structured,
    title = "Structured vs. Unstructured Inputs in {LLM}s: Evaluating the Semantic and Pragmatic Predictive Power in Abnormal Event Forecasting",
    author = "Chi, Jou-An  and
      Hsieh, Shu-Kai",
    editor = "Chang, Kai-Wei  and
      Lu, Ke-Han  and
      Yang, Chih-Kai  and
      Tam, Zhi-Rui  and
      Chang, Wen-Yu  and
      Wang, Chung-Che",
    booktitle = "Proceedings of the 37th Conference on Computational Linguistics and Speech Processing (ROCLING 2025)",
    month = nov,
    year = "2025",
    address = "National Taiwan University, Taipei City, Taiwan",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/dashboard/2025.rocling-main.25/",
    pages = "237--248",
    ISBN = "979-8-89176-379-1",
    abstract = "Large Language Models (LLMs) are increasingly applied to temporally grounded reasoning tasks, yet the role of input representation remains unclear. This paper compares structured temporal inputs, represented as Temporal Knowledge Graphs (TKGs), with unstructured captions in two settings: forecasting future events and detecting anomalies in surveillance video descriptions. To enable direct comparison, we build a unified dataset by aligning anomaly labels from UCF-Crime with caption annotations from UCA. Experiments show that unstructured captions consistently yield slightly higher scores across both tasks, but the differences do not reach statistical significance. Their trade-offs, however, differ: captions provide richer semantic cues for generation, while TKGs reduce input length, suppress noise, and enhance interpretability. These findings suggest that action-centric corpora, such as surveillance or forensic narratives, naturally lend themselves to structured representations, which can provide temporal scaffolds for timeline reconstruction and more traceable reasoning. All code, data processing scripts, and experimental results are available at our GitHub repository."
}