@inproceedings{li-etal-2026-dutirshlee,
    title = "dutirshlee at {S}em{E}val-2026 Task 11: Symbolic Augmentation for Content-Bias-Resistant Syllogistic Reasoning",
    author = "Li, Songhuan  and
      Yang, Liang  and
      Yin, Shengdi  and
      Zhang, Qiang  and
      Lin, Hongfei",
    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-1.73/",
    pages = "509--513",
    ISBN = "979-8-89176-414-9",
    abstract = "We describe our system for SemEval-2026 Task 11 Subtask 1 (English syllogistic validity). Our approach fine-tunes Qwen2.5-7B-Instruct with LoRA and a symbolic data augmentation (SDA) scheme that replaces real-world entities with abstract placeholders, explicitly decoupling logical form from content. The resulting model achieves 96.34{\%} accuracy and a total content effect (TCE) of 2.15, yielding a primary score of 44.86. We provide detailed ablations and negative results (prompting, self consistency, contrastive decoding, structured chain-of-thought, andDPO)tocharacterizewhy direct LoRA training with SDA is the most ro bust configuration for this task. Finally, we use a specialist{--}generalist complementarity setting where a strong API model (ACC 99.48, TCE 1.06, score 57.68) is corrected by the SDA spe cialist on a single disagreement, producing a merged output with ACC 100 and TCE 0."
}