@inproceedings{siddiqu2025on,
author = {Siddiqu, Shoaib Ahmed and Chen, Yanzhi and Heo, Juyeon and Xia, Menglin and Weller, Adrian},
title = {On Evaluating LLMs’ Capabilities as Functional Approximators: A Bayesian Perspective},
booktitle = {COLING 2025},
year = {2025},
month = {January},
abstract = {Recent works have successfully applied Large Language Models (LLMs) to function modelling tasks. However, the reasons behind this success remain unclear. In this work, we propose a new evaluation framework to comprehensively assess LLMs’ function modelling abilities. By adopting a Bayesian perspective of function modelling, 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 modelling.},
url = {http://approjects.co.za/?big=en-us/research/publication/on-evaluating-llm-capabilities-as-functional-approximators/},
}