Lemao Liu, Jie Zhou, Mo Yu, Dit-Yan Yeung, Jiangnan Li, Shunchi Zhang, Junjie Wu, Tsz Ting
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
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, PHYSICO. 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-ofthe-art LLMs, including GPT-4o, o1 and Gemini 2.0 flash thinking, lag behind humans by ∼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.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2502.08946")
get_code_for_paper("2502.08946")
have("2502.08946")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2502.08946.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2502.08946)
Connect an agent — have() is free.