English

On Evaluating LLMs' Capabilities as Functional Approximators: A Bayesian Perspective

Machine Learning 2024-10-08 v1 Artificial Intelligence

Abstract

Recent works have successfully applied Large Language Models (LLMs) to function modeling tasks. However, the reasons behind this success remain unclear. In this work, we propose a new evaluation framework to comprehensively assess LLMs' function modeling abilities. By adopting a Bayesian perspective of function modeling, we discover that LLMs are relatively weak in understanding patterns in raw data, but excel at utilizing prior knowledge about the domain to develop a strong understanding of the underlying function. Our findings offer new insights about the strengths and limitations of LLMs in the context of function modeling.

Keywords

Cite

@article{arxiv.2410.04541,
  title  = {On Evaluating LLMs' Capabilities as Functional Approximators: A Bayesian Perspective},
  author = {Shoaib Ahmed Siddiqui and Yanzhi Chen and Juyeon Heo and Menglin Xia and Adrian Weller},
  journal= {arXiv preprint arXiv:2410.04541},
  year   = {2024}
}
R2 v1 2026-06-28T19:10:24.140Z