@inproceedings{lu-etal-2025-unimath,
    title = "{U}ni{M}ath-{C}o{T}: A Unified Framework for Multimodal Mathematical Reasoning with Re-Inference Affirmation",
    author = "Lu, Zhixiang  and
      Zhou, Mian  and
      Stefanidis, Angelos  and
      Su, Jionglong",
    editor = "Valentino, Marco  and
      Ferreira, Deborah  and
      Thayaparan, Mokanarangan  and
      Ranaldi, Leonardo  and
      Freitas, Andre",
    booktitle = "Proceedings of The 3rd Workshop on Mathematical Natural Language Processing (MathNLP 2025)",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.mathnlp-main.13/",
    pages = "176--185",
    ISBN = "979-8-89176-348-7",
    abstract = "Large Language Models (LLMs) have achieved considerable success in text-based mathematical reasoning, yet their potential remains underexplored in the multimodal mathematics domain where joint text and image understanding is imperative. A key bottleneck hindering progress is the scarcity of high-quality, genuinely multimodal benchmarks. To address this gap, we construct a unified benchmark by consolidating and curating three public multimodal mathematics datasets. We subsequently propose the UniMath-CoT framework, which establishes a robust performance baseline by combining Chain-of-Thought (CoT) principles with efficient Supervised Fine-Tuning (SFT) based on Low-Rank Adaptation (LoRA). Furthermore, to bolster the model{'}s reasoning robustness, we introduce an innovative verification mechanism, AARI (Answer Affirmation by Re-Inference), which leverages a specialized re-inference protocol to have the model self-scrutinize and validate its initial conclusions. Our comprehensive experiments show that this integrated strategy substantially boosts performance, surpassing a wide range of open-source models and markedly closing the gap with leading proprietary systems."
}