@inproceedings{philippov-etal-2026-glite,
    title = "Glite at {BEA} 2026 Shared Task 1: Holistic Difficulty Models Dominate, Feature Engineering Closes the Gap in {L}1-Aware Vocabulary Difficulty Prediction",
    author = "Philippov, Vassili  and
      Andreev, Dmitrii  and
      Katunin, Pavel  and
      Nikolaev, Anton",
    editor = "Kochmar, Ekaterina  and
      Alhafni, Bashar  and
      Bann{\`o}, Stefano  and
      Bexte, Marie  and
      Burstein, Jill  and
      Horbach, Andrea  and
      Laarmann-Quante, Ronja  and
      Tack, Anais  and
      Yaneva, Victoria  and
      Yuan, Zheng",
    booktitle = "Proceedings of the 21st Workshop on Innovative Use of {NLP} for Building Educational Applications ({BEA} 2026)",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.bea-1.77/",
    pages = "1091--1105",
    ISBN = "979-8-89176-409-5",
    abstract = "This paper describes our submission to the BEA 2026 Shared Task on L1-Aware English Vocabulary Difficulty Prediction. We build per-L1 CatBoost regressors over 1,161 candidate linguistic, psycholinguistic, dictionary, and LLM-derived features drawn from 129 feature sets; out-of-fold predictions from fine-tuned encoder and decoder-LLM regression heads enter the model as additional features. Features are selected via Recursive Feature Elimination with nested cross-validation, producing compact per-L1 models of 29-150 features per run. For the closed track we introduce a per-feature-column compliance audit that classifies 57 of 129 feature sets as track-eligible under the organiser rulings, an audit that forced a rebuild of the selection and ensembling pipelines in the final week. We further show that decoder-LLM LoRA regression heads {---} LLaMA-3.1-8B being the single strongest model in our pool {---} provide the largest marginal gains in the open track, and that a simpler per-L1 CatBoost on RFE-selected features matches or exceeds Ridge-stacking ensembles over the same base models. Our systems ranked 1st in the closed track and 2nd in the open track on all three L1s (Spanish, German, Mandarin), reducing baseline RMSE by 29.9{\%} in the closed track and 35.9{\%} in the open track on average."
}