Large Language Models (LLMs) have been observed to perform well on a wide range of downstream tasks when fine-tuned on domain-specific data. However, such data may not be readily available in many applications, motivating zero-shot or few-shot approaches using domain-adjacent models. While several fine-tuned models for various tasks are available, finding an appropriate domain-adjacent model for a given task is often not straight forward. In this paper, we study DAFT-E, a framework that utilizes an Ensemble of Domain-Adjacent Fine-Tuned Foundation Models for few-shot problems. We show that for zero-shot problems, this ensembling method provides an accuracy performance close to that of the single best model. With few-shot problems, this performance improves further, at which point DEFT-E can outperform any single domain-adjacent model while requiring much less data for domain-specific fine-tuning.
@article{arxiv.2406.13720,
title = {On the Utility of Domain-Adjacent Fine-Tuned Model Ensembles for Few-shot Problems},
author = {Md Ibrahim Ibne Alam and Parikshit Ram and Soham Dan and Horst Samulowitz and Koushik Kar},
journal= {arXiv preprint arXiv:2406.13720},
year = {2025}
}
Comments
Main paper is 14 pages, followed by references and appendix