@inproceedings{osuji-etal-2025-scaling,
    title = "Scaling Up Data-to-Text Generation to Longer Sequences: A New Dataset and Benchmark Results for Generation from Large Triple Sets",
    author = "Osuji, Chinonso Cynthia  and
      Mille, Simon  and
      O{'}Connell, Ornait  and
      Castro Ferreira, Thiago  and
      Belz, Anya  and
      Davis, Brian",
    editor = "Flek, Lucie  and
      Narayan, Shashi  and
      Phương, L{\^e} Hồng  and
      Pei, Jiahuan",
    booktitle = "Proceedings of the 18th International Natural Language Generation Conference",
    month = oct,
    year = "2025",
    address = "Hanoi, Vietnam",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/author-page-lei-gao-usc/2025.inlg-main.47/",
    pages = "810--822",
    abstract = "The ability of LLMs to write coherent, faithful long texts from structured data inputs remains relatively uncharted, in part because nearly all public data-to-text datasets contain only short input-output pairs. To address these gaps, we benchmark six LLMs, a rule{-}based system and human-written texts on a new long-input dataset in English and Irish via LLM-based evaluation. We find substantial differences between models and languages."
}