@inproceedings{gunduz-etal-2025-enhancing,
    title = "Enhancing Essay Scoring with {GPT}-2 Using Back Translation Techniques",
    author = "Gunduz, Aysegul  and
      Gierl, Mark  and
      Bulut, Okan",
    editor = "Wilson, Joshua  and
      Ormerod, Christopher  and
      Beiting Parrish, Magdalen",
    booktitle = "Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Full Papers",
    month = oct,
    year = "2025",
    address = "Wyndham Grand Pittsburgh, Downtown, Pittsburgh, Pennsylvania, United States",
    publisher = "National Council on Measurement in Education (NCME)",
    url = "https://preview.aclanthology.org/name-variant-enfa-fane/2025.aimecon-main.44/",
    pages = "406--416",
    ISBN = "979-8-218-84228-4",
    abstract = "This study evaluates GPT-2 (small) for automated essay scoring on the ASAP dataset. Back-translation (English{--}Turkish{--}English) improved performance, especially on imbalanced sets. QWK scores peaked at 0.77. Findings highlight augmentation{'}s value and the need for more advanced, rubric-aware models for fairer assessment."
}