@article{wei-etal-2026-multimodal,
    title = "Do Multimodal {LLM}s Understand Order? Measuring the Fragility of Multimodal Reasoning under Input Order Perturbations",
    author = "Wei, Sheng-Lun  and
      Liao, Yu-Ling  and
      Huang, Hen-Hsen  and
      Chen, Hsin-Hsi",
    editor = "Piperidis, Stelios  and
      Bel, N{\'u}ria  and
      van den Heuvel, Henk  and
      Ide, Nancy  and
      Krek, Simon  and
      Toral, Antonio",
    journal = "International Conference on Language Resources and Evaluation",
    volume = "main",
    month = may,
    year = "2026",
    address = "Palma de Mallorca, Spain",
    publisher = "ELRA Language Resource Association",
    url = "https://preview.aclanthology.org/ingest-lrec/2026.lrec-main.716/",
    pages = "9118--9128",
    abstract = "Multimodal reasoning has progressed rapidly with large vision-language models (LVLMs), yet their robustness under input variations remains underexplored. This study investigates positional bias in LVLMs for multimodal multiple-choice questions. Our analysis shows that model predictions are sensitive to both choice and modality ordering. We conduct a large-scale evaluation on MMMU, CVQA, and MMBench using fourteen representative models. Further analysis examines how question properties, including difficulty, domain, and image type, affect robustness. We also assess whether text-based mitigation strategies transfer to the VQA setting and perform ablation studies on self-consistency and reasoning complexity. Overall, our findings provide the first comprehensive understanding of positional bias from a vision-language perspective, highlighting key challenges in achieving stable multimodal reasoning."
}