@article{subbiah-etal-2024-reading,
    title = "Reading Subtext: Evaluating Large Language Models on Short Story Summarization with Writers",
    author = "Subbiah, Melanie  and
      Zhang, Sean  and
      Chilton, Lydia B.  and
      McKeown, Kathleen",
    journal = "Transactions of the Association for Computational Linguistics",
    volume = "12",
    year = "2024",
    address = "Cambridge, MA",
    publisher = "MIT Press",
    url = "https://preview.aclanthology.org/fix-sig-urls/2024.tacl-1.71/",
    doi = "10.1162/tacl_a_00702",
    pages = "1290--1310",
    abstract = "We evaluate recent Large Language Models (LLMs) on the challenging task of summarizing short stories, which can be lengthy, and include nuanced subtext or scrambled timelines. Importantly, we work directly with authors to ensure that the stories have not been shared online (and therefore are unseen by the models), and to obtain informed evaluations of summary quality using judgments from the authors themselves. Through quantitative and qualitative analysis grounded in narrative theory, we compare GPT-4, Claude-2.1, and LLama-2-70B. We find that all three models make faithfulness mistakes in over 50{\%} of summaries and struggle with specificity and interpretation of difficult subtext. We additionally demonstrate that LLM ratings and other automatic metrics for summary quality do not correlate well with the quality ratings from the writers."
}