@inproceedings{fane-etal-2025-fane,
    title = "Fane at {S}em{E}val-2025 Task 10: Zero-Shot Entity Framing with Large Language Models",
    author = "Fane, Enfa  and
      Surdeanu, Mihai  and
      Blanco, Eduardo  and
      Corman, Steven",
    editor = "Rosenthal, Sara  and
      Ros{\'a}, Aiala  and
      Ghosh, Debanjan  and
      Zampieri, Marcos",
    booktitle = "Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/corrections-2025-08/2025.semeval-1.251/",
    pages = "1924--1934",
    ISBN = "979-8-89176-273-2",
    abstract = "Understanding how news narratives frame entities is crucial for studying media{'}s impact on societal perceptions of events. In this paper, we evaluate the zero-shot capabilities of large language models (LLMs) in classifying framing roles. Through systematic experimentation, we assess the effects of input context, prompting strategies, and task decomposition. Our findings show that a hierarchical approach of first identifying broad roles and then fine-grained roles, outperforms single-step classification. We also demonstrate that optimal input contexts and prompts vary across task levels, highlighting the need for subtask-specific strategies. We achieve a Main Role Accuracy of 89.4{\%} and an Exact Match Ratio of 34.5{\%}, demonstrating the effectiveness of our approach. Our findings emphasize the importance of tailored prompt design and input context optimization for improving LLM performance in entity framing."
}