Document type
Master thesisPublication date
Publication license
Please use this identifier to cite or link to this item: https://hdl.handle.net/2445/223156
Enhancing Few-Shot Learning with Large Language Models
Journal Title
Authors
Director/Tutor
Journal ISSN
Volume Title
Related resource
Abstract
Recently, Few-Shot Learning has gained significant momentum in the machine learning community. This field focuses on enabling models to learn from extremely limited data, often just a handful of examples per class. Unlike traditional deep learning, which relies on large-scale datasets, few-shot learning requires novel, efficient strategies that challenge conventional assumptions and fundamentally shift the paradigm toward "learning to learn", for faster, more adaptable models.
In this work, we explore the most common approaches to few-shot learning and introduce our own method. Building upon the SemFew framework, we propose a metric-based meta-learning approach using Prototypical Networks, enhanced with a semantic support module. This module uses class descriptions from WordNet,
refined through a Large Language Model, to provide high-quality semantic embeddings that guide the model in understanding novel classes. Our proposed model is remarkably simple yet highly effective, achieving competitive performance with state-of-the-art methods, specially in 1-shot scenarios (only one example per class).
We validate our method across three widely used few-shot classification benchmarks: CIFAR-FS, FC100, and MiniImageNet. The results consistently demonstrate the effectiveness of incorporating semantic guidance to face unseen classes. Further-more, we present an in-depth study of modern LLMs, evaluating their performance
across different prompting strategies, and investigating multiple sources of data for generating the best semantic representations. This analysis offers valuable insights into how semantic guidance can be optimized for few-shot learning. Overall, this work demonstrates the power of combining simple metric-based learning with rich semantic embeddings, offering a practical and competitive alternative to more complex architectures while encouraging new directions for future research in few-shot learning.
The source code is available at: https://github.com/jdieguvi15/TFM-SemFew.
Description
Treballs finals del Màster de Fonaments de Ciència de Dades, Facultat de matemàtiques, Universitat de Barcelona. Any: 2025. Tutor: Petia Radeva i Javier Ródenas Cumplido
Citation
Citation
DIÉGUEZ VILÀ, Joel. Enhancing Few-Shot Learning with Large Language Models. [consulted: 9 of August of 2026]. Available at: https://hdl.handle.net/2445/223156