<![CDATA[In the area of natural language processing (NLP), especially regarding text classification, earlier methods that relied on traditional machine learning are being increasingly replaced by neural network designs like convolutional neural networks and recurrent neural networks. Additionally, the rise of transformer-based models has led to considerable improvements in performance, though this comes with higher demands for computing power and energy usage. This paper provides a look back at the development of deep learning and Parameter-Efficient Fine-Tuning (PEFT) methods for text classification from 2005 to 2025. The research explores important technological advancements, evaluates the balance between performance, scalability, and efficient computing, and points out the rising concern for sustainability in the development of artificial intelligence. The findings show a transition from strategies aimed at simply increasing scale to those that focus on more efficiency. In this setting, PEFT has become an important advancement in easing the computing load without greatly impacting performance, although it still faces challenges in flexibility and energy consciousness. These insights are anticipated to lay the groundwork for more research into creating environmentally friendly NLP technologies.]]>
Copyrights © 2026
