@inproceedings{jin-etal-2025-revisiting,
    title = "Revisiting 3{D} {LLM} Benchmarks: Are We Really Testing 3{D} Capabilities?",
    author = "Jin, Jiahe  and
      He, Yanheng  and
      Yang, Mingyan",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/corrections-2025-08/2025.findings-acl.1222/",
    doi = "10.18653/v1/2025.findings-acl.1222",
    pages = "23858--23869",
    ISBN = "979-8-89176-256-5",
    abstract = "In this work, we identify the ``2D-Cheating'' problem in 3D LLM evaluation, where these tasks might be easily solved by VLMs with rendered images of point clouds, exposing ineffective evaluation of 3D LLMs' unique 3D capabilities. We test VLM performance across multiple 3D LLM benchmarks and, using this as a reference, propose principles for better assessing genuine 3D understanding. We also advocate explicitly separating 3D abilities from 1D or 2D aspects when evaluating 3D LLMs."
}