Language Models for Text Classification: Is In-Context Learning Enough?

arXiv:2403.17661v1 Announce Type: new
Abstract: Recent foundational language models have shown state-of-the-art performance in many NLP tasks in zero- and few-shot settings. An advantage of these models over more standard approaches based on fine-tuning is the ability to understand instructions written in natural language (prompts), which helps them generalise better to different tasks and domains without the need for specific training data. This makes them suitable for addressing text classification problems for domains with limited amounts of annotated instances. However, …

abstract art arxiv classification context cs.ai cs.cl few-shot fine-tuning foundational in-context learning language language models natural natural language nlp performance prompts standard state tasks text text classification them type