Scikit-LLM: Beginner Friendly NLP Using LLMs

Abstract

The instruction following and in-context learning capabilities of LLMs make them suitable for tackling many NLP tasks. In this talk, we will introduce Scikit-LLM, a rapidly growing, beginner-friendly library that abstracts the complexity of working with LLMs by providing a scikit-learn compatible API. We will showcase how Scikit-LLM can be utilized for solving text classification and text-to-text tasks, and will delve deeper into various methods to improve the model performance, such as prompting strategies and fine-tuning.