@inproceedings{liu-etal-2026-mirrorqa,
    title = "{M}irror{QA}: Benchmarking Multimodal {LLM}s on Mirror-Orientation Reasoning",
    author = "Liu, Jingping  and
      Peng, Xingchen  and
      Zhou, Yan  and
      Liu, Ziyan  and
      Zhai, Jie  and
      Chen, Ronghao  and
      Wang, Huacan  and
      Jia, Xiaofeng",
    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.1879/",
    pages = "40464--40476",
    ISBN = "979-8-89176-390-6",
    abstract = "Multimodal large language models (MLLMs) have achieved remarkable progress in recent years, yet their ability to perform left{--}right reasoning in mirror contexts{---}a fundamental element of spatial cognition{---}remains underexplored. To address this gap, we introduce MirrorQA, a manually constructed benchmark with 5,549 samples, designed to evaluate MLLMs' capability to distinguish left from right from a subject-centered perspective. MirrorQA is built through a three-stage pipeline (annotation, verification, and final review) to ensure high-quality labeling. Comprehensive evaluations on both open- and closed-source MLLMs show that even the best-performing models achieve only 65.40{\%} accuracy, far below the 99.28{\%} accuracy of humans. These results highlight substantial challenges in current MLLMs when reasoning about left and right, and point to promising directions for future research. MirrorQA and its code are publicly available at anonymous link https://github.com/stargazer-zeno/MirrorQA."
}