@inproceedings{ionov-etal-2025-smurfcat,
    title = "{S}murf{C}at at {SHROOM}-{CAP}: Factual but Awkward? Fluent but Wrong? Tackling Both in {LLM} Scientific {QA}",
    author = "Ionov, Timur  and
      Nikolaev, Evgenii  and
      Vazhentsev, Artem  and
      Chaichuk, Mikhail  and
      Korznikov, Anton  and
      Tutubalina, Elena  and
      Panchenko, Alexander  and
      Konovalov, Vasily  and
      Rykov, Elisei",
    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.8/",
    pages = "81--89",
    ISBN = "979-8-89176-308-1",
    abstract = "Large Language Models (LLMs) often generate hallucinations, a critical issue in domains like scientific communication where factual accuracy and fluency are essential. The SHROOM-CAP shared task addresses this challenge by evaluating Factual Mistakes and Fluency Mistakes across diverse languages, extending earlier SHROOM editions to the scientific domain. We present Smurfcat, our system for SHROOM-CAP, which integrates three complementary approaches: uncertainty estimation (white-box and black-box signals), encoder-based classifiers (Multilingual Modern BERT), and decoder-based judges (instruction-tuned LLMs with classification heads). Results show that decoder-based judges achieve the strongest overall performance, while uncertainty methods and encoders provide complementary strengths. Our findings highlight the value of combining uncertainty signals with encoder and decoder architectures for robust, multilingual detection of hallucinations and related errors in scientific publications."
}