LLMs as In-Context Meta-Learners for Model and Hyperparameter Selection

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hili, Youssef Attia El, Thomas, Albert, Tiomoko, Malik, Benechehab, Abdelhakim, Léger, Corentin, Ancourt, Corinne, Kégl, Balázs
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917273378226176
author Hili, Youssef Attia El
Thomas, Albert
Tiomoko, Malik
Benechehab, Abdelhakim
Léger, Corentin
Ancourt, Corinne
Kégl, Balázs
author_facet Hili, Youssef Attia El
Thomas, Albert
Tiomoko, Malik
Benechehab, Abdelhakim
Léger, Corentin
Ancourt, Corinne
Kégl, Balázs
contents Model and hyperparameter selection are critical but challenging in machine learning, typically requiring expert intuition or expensive automated search. We investigate whether large language models (LLMs) can act as in-context meta-learners for this task. By converting each dataset into interpretable metadata, we prompt an LLM to recommend both model families and hyperparameters. We study two prompting strategies: (1) a zero-shot mode relying solely on pretrained knowledge, and (2) a meta-informed mode augmented with examples of models and their performance on past tasks. Across synthetic and real-world benchmarks, we show that LLMs can exploit dataset metadata to recommend competitive models and hyperparameters without search, and that improvements from meta-informed prompting demonstrate their capacity for in-context meta-learning. These results highlight a promising new role for LLMs as lightweight, general-purpose assistants for model selection and hyperparameter optimization.
format Preprint
id arxiv_https___arxiv_org_abs_2510_26510
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LLMs as In-Context Meta-Learners for Model and Hyperparameter Selection
Hili, Youssef Attia El
Thomas, Albert
Tiomoko, Malik
Benechehab, Abdelhakim
Léger, Corentin
Ancourt, Corinne
Kégl, Balázs
Machine Learning
Model and hyperparameter selection are critical but challenging in machine learning, typically requiring expert intuition or expensive automated search. We investigate whether large language models (LLMs) can act as in-context meta-learners for this task. By converting each dataset into interpretable metadata, we prompt an LLM to recommend both model families and hyperparameters. We study two prompting strategies: (1) a zero-shot mode relying solely on pretrained knowledge, and (2) a meta-informed mode augmented with examples of models and their performance on past tasks. Across synthetic and real-world benchmarks, we show that LLMs can exploit dataset metadata to recommend competitive models and hyperparameters without search, and that improvements from meta-informed prompting demonstrate their capacity for in-context meta-learning. These results highlight a promising new role for LLMs as lightweight, general-purpose assistants for model selection and hyperparameter optimization.
title LLMs as In-Context Meta-Learners for Model and Hyperparameter Selection
topic Machine Learning
url https://arxiv.org/abs/2510.26510