@article{eltanbouly-etal-2026-one,
    title = "Is One Dataset Enough for Evaluation? Studying Generalizability of Automated Essay Scoring Models",
    author = "Eltanbouly, Sohaila  and
      Sayed, Marwan  and
      Elsayed, Tamer",
    editor = "Piperidis, Stelios  and
      Bel, N{\'u}ria  and
      van den Heuvel, Henk  and
      Ide, Nancy  and
      Krek, Simon  and
      Toral, Antonio",
    journal = "International Conference on Language Resources and Evaluation",
    volume = "main",
    month = may,
    year = "2026",
    address = "Palma de Mallorca, Spain",
    publisher = "ELRA Language Resource Association",
    url = "https://preview.aclanthology.org/ingest-lrec/2026.lrec-main.29/",
    pages = "431--440",
    abstract = "Automated Essay Scoring (AES) has made significant advancements in writing assessment. Recently, cross-prompt AES has gained attention because of its focus on generalizing to unseen prompts. Despite the promise of these advancements, a critical question remains: how generalizable and robust are those models when applied to diverse datasets? This study assesses the generalizability of eight cross-prompt AES models across three different datasets. We employ two experimental setups: the within-dataset approach, where both training and testing occur on the same dataset, and the cross-dataset approach, which challenges the models by evaluating their performance on previously unseen datasets. The experimental results show significant performance inconsistencies, highlighting that relying on a single dataset is insufficient for building robust and generalizable AES systems."
}