Guardado en:
Detalles Bibliográficos
Autores principales: Chou, Tzu-Hsuan, Chou, Chun-Nan
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2511.14738
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866909911608197120
author Chou, Tzu-Hsuan
Chou, Chun-Nan
author_facet Chou, Tzu-Hsuan
Chou, Chun-Nan
contents Large language models (LLMs) have shown a remarkable ability to generalize beyond their pre-training data, and fine-tuning LLMs can elevate performance to human-level and beyond. However, in real-world scenarios, lacking labeled data often prevents practitioners from obtaining well-performing models, thereby forcing practitioners to highly rely on prompt-based approaches that are often tedious, inefficient, and driven by trial and error. To alleviate this issue of lacking labeled data, we present a learning framework integrating LLMs with active learning for unlabeled dataset (LAUD). LAUD mitigates the cold-start problem by constructing an initial label set with zero-shot learning. Experimental results show that LLMs derived from LAUD outperform LLMs with zero-shot or few-shot learning on commodity name classification tasks, demonstrating the effectiveness of LAUD.
format Preprint
id arxiv_https___arxiv_org_abs_2511_14738
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LAUD: Integrating Large Language Models with Active Learning for Unlabeled Data
Chou, Tzu-Hsuan
Chou, Chun-Nan
Machine Learning
Large language models (LLMs) have shown a remarkable ability to generalize beyond their pre-training data, and fine-tuning LLMs can elevate performance to human-level and beyond. However, in real-world scenarios, lacking labeled data often prevents practitioners from obtaining well-performing models, thereby forcing practitioners to highly rely on prompt-based approaches that are often tedious, inefficient, and driven by trial and error. To alleviate this issue of lacking labeled data, we present a learning framework integrating LLMs with active learning for unlabeled dataset (LAUD). LAUD mitigates the cold-start problem by constructing an initial label set with zero-shot learning. Experimental results show that LLMs derived from LAUD outperform LLMs with zero-shot or few-shot learning on commodity name classification tasks, demonstrating the effectiveness of LAUD.
title LAUD: Integrating Large Language Models with Active Learning for Unlabeled Data
topic Machine Learning
url https://arxiv.org/abs/2511.14738