NJUSTKMG at SemEval 2026 Task 10 PsyCoMark—Subtask 2:Conspiracy Detection

AbstractThis 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.