LLM-SR: Scientific Equation Discovery via Programming with Large Language Models

arXiv:2404.18400v1 Announce Type: new
Abstract: Mathematical equations have been unreasonably effective in describing complex natural phenomena across various scientific disciplines. However, discovering such insightful equations from data presents significant challenges due to the necessity of navigating extremely high-dimensional combinatorial and nonlinear hypothesis spaces. Traditional methods of equation discovery largely focus on extracting equations from data alone, often neglecting the rich domain-specific prior knowledge that scientists typically depend on. To bridge this gap, we introduce LLM-SR, a novel approach that leverages …

abstract arxiv challenges cs.ai cs.cl cs.lg cs.ne data discovery equation focus however hypothesis language language models large language large language models llm mathematical equations natural programming scientific spaces type via