User Modeling in the Era of Large Language Models: Current Research and Future Directions

TL;DR

LLMs enable advanced user modeling by leveraging UGC and interactions, bridging text and graph modalities. The paper surveys LLM-UM approaches organized around four roles (predictors, enhancers, controllers, evaluators) and two application goals (personalization and suspiciousness detection). It reviews text- and graph-based UM techniques, presents representative methods and applications, and discusses challenges such as hallucinations, privacy, fairness, and domain adaptation. It highlights future directions and provides a reading list for researchers.

Abstract

User modeling (UM) aims to discover patterns or learn representations from user data about the characteristics of a specific user, such as profile, preference, and personality. The user models enable personalization and suspiciousness detection in many online applications such as recommendation, education, and healthcare. Two common types of user data are text and graph, as the data usually contain a large amount of user-generated content (UGC) and online interactions. The research of text and graph mining is developing rapidly, contributing many notable solutions in the past two decades. Recently, large language models (LLMs) have shown superior performance on generating, understanding, and even reasoning over text data. The approaches of user modeling have been equipped with LLMs and soon become outstanding. This article summarizes existing research about how and why LLMs are great tools of modeling and understanding UGC. Then it reviews a few categories of large language models for user modeling (LLM-UM) approaches that integrate the LLMs with text and graph-based methods in different ways. Then it introduces specific LLM-UM techniques for a variety of UM applications. Finally, it presents remaining challenges and future directions in the LLM-UM research. We maintain the reading list at: https://github.com/TamSiuhin/LLM-UM-Reading

Figures (6)

• Figure 1: User modeling aims to discover knowledge and patterns from user data to identify profile, preference, and personality. The three blue arrows in the figure correspond to our three major contributions: (1) summarize how and why LLMs are great tools for modeling and understanding UGC, (2) review approaches that integrate LLMs with text- and graph-based UM methods, and (3) introduce LLM-UM techniques for various applications.
• Figure 2: Structure of this survey.
• Figure 3: Some examples of LLMs for recommendation, rating prediction, user profiling, personality analysis, and hate speech detection. They serve as compelling examples that demonstrate the ability of LLMs to effectively model, comprehend, and reason based on user-generated content (UGC) and user interactions.
• Figure 4: LLMs-as-Predictors, where LLMs are exclusively utilized to generate the predicted response.
• Figure 5: LLMs-as-Enhancers, where LLMs are leveraged to generate user profiles, content embeddings, knowledge-augmented content, and training data to augment downstream user modeling systems.