@inproceedings{parashar-mathias-2026-token,
    title = "Token Titans at {BEA} 2026 Shared Task 1: Multilingual Lexical Complexity Prediction via Fine-Tuned {XLM}-{R}o{BERT}a with Ensemble Decoding",
    author = "Parashar, Anubhab  and
      Mathias, Sandeep",
    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-1.80/",
    pages = "1119--1123",
    ISBN = "979-8-89176-409-5",
    abstract = "We describe our submission to the BEA 2026 Shared Task on Multilingual Lexical Complexity Prediction. The system fine-tunes XLM-RoBERTa Large separately for Spanish, German, and Chinese, feeding each instance as a flat concatenation of the source word, its sentential context, an English clue, and the English target word. Training uses z-score label normalization and two independent runs thatdiffer in learning rate, scheduler, and random seed; a weighted ensemble of their predictions (0.6/0.4) consistently reduces variance on the validation set. On the official test set the system scores RMSE = 1.170 and Pearson = 0.812."
}