@inproceedings{r-2025-scalar,
    title = "{S}calar{\_}{NITK} at {SHROOM}-{CAP}: Multilingual Factual Hallucination and Fluency Error Detection in Scientific Publications Using Retrieval-Guided Evidence and Attention-Based Feature Fusion",
    author = "R, Anjali",
    editor = {Sinha, Aman  and
      V{\'a}zquez, Ra{\'u}l  and
      Mickus, Timothee  and
      Agarwal, Rohit  and
      Buhnila, Ioana  and
      Schmidtov{\'a}, Patr{\'i}cia  and
      Gamba, Federica  and
      Prasad, Dilip K.  and
      Tiedemann, J{\"o}rg},
    booktitle = "Proceedings of the 1st Workshop on Confabulation, Hallucinations and Overgeneration in Multilingual and Practical Settings (CHOMPS 2025)",
    month = dec,
    year = "2025",
    address = "Mumbai, India",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-ijcnlp-aacl/2025.chomps-main.9/",
    pages = "90--95",
    ISBN = "979-8-89176-308-1",
    abstract = "One of the key challenges of deploying Large Language Models (LLMs) in multilingual scenarios is maintaining output quality across two conditions: factual correctness and linguistic fluency. LLMs are liable to produce text with factual hallucinations, solid-sounding but false information, and fluency errors that take the form of grammatical mistakes, repetition, or unnatural speech patterns. In this paper, we address a two-framework solution for the end-to-end quality evaluation of LLM-generated text in low-resource languages.(1) For hallucination detection, we introduce a retrieval-augmented classification model that utilizes hybrid document retrieval, along with gradient boosting.(2) For fluency detection, we introduce a deep learning model that combines engineered statistical features with pre-trained semantic embeddings using an attention-based mechanism."
}