@inproceedings{chundru-etal-2025-llms,
    title = "Do {LLM}s Encode Frame Semantics? Evidence from Frame Identification",
    author = "Chundru, Jayanth Krishna  and
      Poddar, Rudrashis  and
      Cao, Jie  and
      Jiang, Tianyu",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-main.1499/",
    pages = "29476--29488",
    ISBN = "979-8-89176-332-6",
    abstract = "We investigate whether large language models encode latent knowledge of frame semantics, focusing on frame identification, a core challenge in frame semantic parsing that involves selecting the appropriate semantic frame for a target word in context. Using the FrameNet lexical resource, we evaluate models under prompt-based inference and observe that they can perform frame identification effectively even without explicit supervision. To assess the impact of task-specific training, we fine-tune the model on FrameNet data, which substantially improves in-domain accuracy while generalizing well to out-of-domain benchmarks. Further analysis shows that the models can generate semantically coherent frame definitions, highlighting the model{'}s internalized understanding of frame semantics."
}