On Evaluating LLMs’ Capabilities as Functional Approximators: A Bayesian Evaluation Framework

Shoaib Ahmed Siddiqui, Yanzhi Chen, Juyeon Heo, Menglin Xia, Adrian Weller


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.
Anthology ID:
2025.coling-main.388
Volume:
Proceedings of the 31st International Conference on Computational Linguistics
Month:
January
Year:
2025
Address:
Abu Dhabi, UAE
Editors:
Owen Rambow, Leo Wanner, Marianna Apidianaki, Hend Al-Khalifa, Barbara Di Eugenio, Steven Schockaert
Venue:
COLING
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5826–5835
Language:
URL:
https://aclanthology.org/2025.coling-main.388/
DOI:
Bibkey:
Cite (ACL):
Shoaib Ahmed Siddiqui, Yanzhi Chen, Juyeon Heo, Menglin Xia, and Adrian Weller. 2025. On Evaluating LLMs’ Capabilities as Functional Approximators: A Bayesian Evaluation Framework. In Proceedings of the 31st International Conference on Computational Linguistics, pages 5826–5835, Abu Dhabi, UAE. Association for Computational Linguistics.
Cite (Informal):
On Evaluating LLMs’ Capabilities as Functional Approximators: A Bayesian Evaluation Framework (Siddiqui et al., COLING 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.coling-main.388.pdf