Skip to content
Book Open access

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

Aug 2026 · Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2 · pp. 13370-13374 · 0 citations · 59 references

TL;DR

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.

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.

Read PDF

Similar papers

Book Open access Sep 2026

GradSup: Gradient Superposition for Personalised and Scalable LLM Recommendation

Large language models (LLMs) have demonstrated strong capabilities in recommendation tasks such as item, sequence, conversational recommendation, and explanation generation. However, LLM weights are typically shared across all users. Adapting these models to individual users remains a fundamental challenge that require...

Kanishka Dandeniya, C. Dasanayaka, Daswin de Silva et al. · 0 citations
Review Open access Oct 2026

A Survey on Large Language Models for Recommendation Systems

This paper systematically reviews recent advances in LLM-empowered recommendation systems, and analyzes major challenges related to hallucination, inference efficiency, privacy and security, fairness and trustworthiness, and recommendation agents.

Jun-Lei Yang · 0 citations
#artificial intelligence Conference Open access Oct 2026

MoF: Preference-Aware Mixture Modeling for Black-Box LLM Personalization

Proprietary Large Language Models (LLMs) have demonstrated remarkable capabilities across a wide range of tasks, yet aligning their outputs with diverse user preferences remains challenging. Existing personalization approaches for black-box LLMs often rely on user-specific scoring heads, causing the number of personali...

Hun Park · 0 citations
#artificial intelligence Open access Sep 2026

COPE: Continual Personalization of LLMs under Sparse User Feedback via User Embeddings and Self-Evaluation

Experiments show that COPE consistently outperforms strong training-free and training-based baselines under sparse feedback, and remains complementary to Retrieval-Augmented Prompting, and further analyses confirm COPE's reliable self-evaluation, meaningful preference patterns, stable general capabilities, and robustne...

Rui-Ke Cao, Fu-Gen Yao, Liang Dong et al. · 0 citations
#artificial intelligence Review Sep 2026

Aplaud: Adaptive Personalized Low-Rank Decomposition for User-Specific LLM

Aplaud (Adaptive Personalized Low-rank and User-specific Nested Decomposition), a lightweight and scalable framework for LLM personalization that outperforms state-of-the-art LoRA-based personalized LLM approaches in both generalization and inference efficiency.

Xin-Yu Li, Ruo-Ming Jin, Jian-Feng Zhu et al. · 1 citation

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.