From Generic Intelligence to Personalized AI: A Tutorial on Foundations of LLM Personalization

Abstract

Large language models (LLMs) have achieved remarkable success across diverse applications, yet their generic training paradigm limits effectiveness in user-specific scenarios. LLM personalization aims to adapt large models to individual users or user groups by incorporating preferences, histories, and contextual signals while maintaining generalization ability. Despite growing interest, a unified understanding of personalization strategies for LLMs remains lacking, and key challenges—including data scarcity, efficiency, privacy, and fairness—are still open. This tutorial provides a systematic overview of LLM personalization, covering core paradigms such as user-aware representations, prompt-based adaptation, memory augmentation, parameter-efficient fine-tuning, and continual learning. We discuss evaluation protocols, theoretical foundations, and real-world applications in recommendation, dialogue systems, education, and healthcare. By synthesizing recent advances and identifying emerging research directions, this tutorial aims to equip the KDD community with a structured framework for advancing personalized large model research and deployment.