@inproceedings{chen-etal-2026-parasuite,
    title = "{P}ara{S}uite: Boosting {LLM} Reasoning via Paradox Resolution",
    author = "Chen, Bin  and
      Zhang, Yu  and
      Ye, Hongfei  and
      Wang, Huiyang  and
      Liu, Wenxi  and
      Chen, Hongyang",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.2047/",
    pages = "44246--44256",
    ISBN = "979-8-89176-390-6",
    abstract = "Logical reasoning is a key capability of large language models, yet current benchmarks focus almost entirely on tasks that just check basic logical consistency and overlook the reflective reasoning required for paradox detection and resolution. To fill the gap, we present ParaSuite, the first pipeline dedicated to paradox research that automates data synthesis, evaluation, and training. We introduce PARADOX, a synthetic, high-quality data spanning two difficulty tiers and three academic domains, accompanied by specialized evaluation metrics and solving algorithms. We propose ParadoxBreaker-7B, trained with Mutual-Information Guided Fine-Tuning and reinforcement learning step verify paradox reward(PAPO). Experiments demonstrate significant improvements in both paradoxical and general STEM reasoning."
}