@inproceedings{zheng-yang-2026-njustkmg,
    title = "{NJUSTKMG} at {S}em{E}val 2026 Task 10 {P}sy{C}o{M}ark{---}Subtask 2:Conspiracy Detection",
    author = "Zheng, Yuhan  and
      Yang, Yang",
    editor = "Kochmar, Ekaterina  and
      Ghosh, Debanjan  and
      North, Kai  and
      Komachi, Mamoru",
    booktitle = "Proceedings of the 20th {I}nternational {W}orkshop on {S}emantic {E}valuation (2026)",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.semeval-1.128/",
    pages = "932--937",
    ISBN = "979-8-89176-414-9",
    abstract = "This paper describes our system designed forSemEval-2026 Task 10: PsyCoMark{---}Subtask2: Conspiracy Detection. We proposed a two-stage approach that leverages large-scale pre-trained models and a fine-tuned smaller modelto detect conspiracy theories in text. In thefirst stage, we utilize a large model to test allthe test samples and filter out those that areclearly unrelated to conspiracy theories. Forthe remaining samples, we apply a retrieval-enhanced custom prompt strategy combinedwith the Roberta-Large model in the secondstage. This allows us to fine-tune the modelwith weighted predictions based on relevantretrieved information, enhancing detection ac-curacy. Our system achieved first place onthe leaderboard, with an impressive F1 Scoreof 0.8874. We also present a brief analysisof the effectiveness of the methods used, in-cluding the advantages and limitations of largemodel-based filtering and retrieval-augmentedfine-tuning."
}