@inproceedings{zhou-etal-2025-miceval,
    title = "{M}i{CE}val: Unveiling Multimodal Chain of Thought{'}s Quality via Image Description and Reasoning Steps",
    author = "Zhou, Xiongtao  and
      He, Jie  and
      Chen, Lanyu  and
      Li, Jingyu  and
      Chen, Haojing  and
      Gutierrez Basulto, Victor  and
      Pan, Jeff Z.  and
      Chen, Hanjie",
    editor = "Chiruzzo, Luis  and
      Ritter, Alan  and
      Wang, Lu",
    booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
    month = apr,
    year = "2025",
    address = "Albuquerque, New Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2025.naacl-long.504/",
    pages = "10002--10039",
    ISBN = "979-8-89176-189-6",
    abstract = "**Multimodal Chain of Thought (MCoT)** is a popular prompting strategy for improving the performance of multimodal large language models (MLLMs) across a range of complex reasoning tasks. Despite its popularity, there is a notable absence of automated methods for evaluating the quality of reasoning steps in MCoT. To address this gap, we propose **Multimodal Chain-of-Thought Evaluation (MiCEval)**, a framework designed to assess the correctness of reasoning chains by evaluating the quality of both the description and each reasoning step. The evaluation of the description component focuses on the accuracy of the image descriptions, while the reasoning step evaluates the quality of each step as it is conditionally generated based on the preceding steps. MiCEval is built upon a fine-grained dataset with annotations that rate each step according to correctness, relevance, and informativeness. Extensive experiments on four state-of-the-art MLLMs show that step-wise evaluations using MiCEval align more closely with human judgments compared to existing methods based on cosine similarity or fine-tuning approaches. MiCEval datasets and code can be found at: [https://anonymous{\_}github/MicEval](https://anonymous.4open.science/r/MiCEval-847F/README.md)."
}