Papers › The Stochastic Parrot on LLM's Shoulder: A Summative Assessment of Physical Concept...

The Stochastic Parrot on LLM's Shoulder: A Summative Assessment of Physical Concept Understanding

13 Feb 2025arXiv:2502.08946archive 2025-07-28

Mo Yu, Lemao Liu, Junjie Wu, Tsz Ting Chung, Shunchi Zhang, Jiangnan Li, Dit-yan Yeung, Jie zhou

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-of-the-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.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

physico-benchmark/physico officialmentioned on GitHub report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

In-Context LearningMemorization

Datasets

Introduced by this paper, per the archive.

PhysiCo

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AttentionLSTMLinear LayerParrotSigmoid ActivationSoftmaxTanh Activation

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections