On the Utility of Domain-Adjacent Fine-Tuned Model Ensembles for Few-shot Problems

Autor:	Alam, Md Ibrahim Ibne, Ram, Parikshit, Dan, Soham, Samulowitz, Horst, Kar, Koushik
Rok vydání:	2024
Předmět:	Computer Science - Computation and Language Computer Science - Machine Learning
Druh dokumentu:	Working Paper
Popis:	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. Comment: Main paper is 8 pages, followed by limitations, references and appendix
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2406.13720 Zobrazit plný text záznamu View this record from Arxiv