@inproceedings{aryal-akomoize-2025-howard,
    title = "{H}oward {U}niversity - {AI}4{PC} at {S}em{E}val-2025 Task 3: Logit-based Supervised Token Classification for Multilingual Hallucination Span Identification Using {XGBOD}",
    author = "Aryal, Saurav  and
      Akomoize, Mildness",
    editor = "Rosenthal, Sara  and
      Ros{\'a}, Aiala  and
      Ghosh, Debanjan  and
      Zampieri, Marcos",
    booktitle = "Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/corrections-2025-08/2025.semeval-1.236/",
    pages = "1790--1794",
    ISBN = "979-8-89176-273-2",
    abstract = "This paper describes our system for SemEval-2025 Task 3, Mu-SHROOM, which focuses on detecting hallucination spans in multilingual LLM outputs. We reframe hallucination detection as a point-wise anomaly detection problem by treating logits as time-series data. Our approach extracts features from token-level logits, addresses class imbalance with SMOTE, and trains an XGBOD model for probabilistic character-level predictions. Our system, which relies solely on information derived from the logits and token offsets (using pretrained tokenizers), achieves competitive intersection-over-union (IoU) and correlation scores on the validation and test set."
}