In-Context Symbolic Regression: Leveraging Language Models for Function Discovery

arXiv:2404.19094v1 Announce Type: cross
Abstract: Symbolic Regression (SR) is a task which aims to extract the mathematical expression underlying a set of empirical observations. Transformer-based methods trained on SR datasets detain the current state-of-the-art in this task, while the application of Large Language Models (LLMs) to SR remains unexplored. This work investigates the integration of pre-trained LLMs into the SR pipeline, utilizing an approach that iteratively refines a functional form based on the prediction error it achieves on the observation …

abstract application art arxiv context cs.cl cs.lg current datasets discovery extract function language language models large language large language models llms regression set state transformer type while work