@inproceedings{yu-etal-2025-stochastic,
    title = "The Stochastic Parrot on {LLM}{'}s Shoulder: A Summative Assessment of Physical Concept Understanding",
    author = "Yu, Mo  and
      Liu, Lemao  and
      Wu, Junjie  and
      Chung, Tsz Ting  and
      Zhang, Shunchi  and
      Li, Jiangnan  and
      Yeung, Dit-Yan  and
      Zhou, Jie",
    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.569/",
    pages = "11416--11431",
    ISBN = "979-8-89176-189-6",
    abstract = "In a systematic way, we investigate a widely asked question: Do LLMs really understand what they say?, which relates to the more familiar term Stochastic Parrot. To this end, we propose a summative assessment over a carefully designed physical concept understanding task, P HYSI C O. Our task alleviates the memorization issue via the usage of grid-format inputs that abstractly describe physical phenomena. The grids represents varying levels of understanding, from the core phenomenon, application examples to analogies to other abstract patterns in the grid world. A comprehensive study on our task demonstrates: (1) state-of-the-art LLMs, including GPT-4o, o1 and Gemini 2.0 flash thinking, lag behind humans by {\ensuremath{\sim}}40{\%}; (2) the stochastic parrot phenomenon is present in LLMs, as they fail on our grid task but can describe and recognize the same concepts well in natural language; (3) our task challenges the LLMs due to intrinsic difficulties rather than the unfamiliar grid format, as in-context learning and fine-tuning on same formatted data added little to their performance."
}