A new benchmark of 380 principle-based physics problems shows that state-of-the-art LLMs struggle to apply symmetry, conservation, and dimensional-analysis shortcuts, achieving under 50 percent average accuracy with high token usage.
Llm-sr: Scientific equation discovery via programming with large language models,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
REJECT 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
PhySense: Principle-Based Physics Reasoning Benchmarking for Large Language Models
A new benchmark of 380 principle-based physics problems shows that state-of-the-art LLMs struggle to apply symmetry, conservation, and dimensional-analysis shortcuts, achieving under 50 percent average accuracy with high token usage.