Parameter-Efficient Fine-Tuning for Policy Documents Classification: Achieving Research Grade Performance with Low-Rank Adaptation of Large Language Models

• In Event: Classification and LLMs

Brief Overview

In this paper, I evaluate whether parameter-efficient fine-tuning methods (PEFT), specifically Low-Rank Adaptation (LoRA), can match the performance of a fully fine-tuned XLM-RoBERTa model for policy document classification.

Author

• Hanif Sajid, University of North Carolina at Charlotte