When Large Language Models Meet Personalization: Perspectives of Challenges and Opportunities

Abstract

The advent of large language models marks a revolutionary breakthrough in artificial intelligence. With the unprecedented scale of training and model parameters, the capability of large language models has been dramatically improved, leading to human-like performances in understanding, language synthesizing, and common-sense reasoning, etc. Such a major leap-forward in general AI capacity will change the pattern of how personalization is conducted. For one thing, it will reform the way of interaction between humans and personalization systems. Instead of being a passive medium of information filtering, large language models present the foundation for active user engagement. On top of such a new foundation, user requests can be proactively explored, and user's required information can be delivered in a natural and explainable way. For another thing, it will also considerably expand the scope of personalization, making it grow from the sole function of collecting personalized information to the compound function of providing personalized services. By leveraging large language models as general-purpose interface, the personalization systems may compile user requests into plans, calls the functions of external tools to execute the plans, and integrate the tools' outputs to complete the end-to-end personalization tasks. Today, large language models are still being developed, whereas the application in personalization is largely unexplored. Therefore, we consider it to be the right time to review the challenges in personalization and the opportunities to address them with LLMs. In particular, we dedicate this perspective paper to the discussion of the following aspects: the development and challenges for the existing personalization system, the newly emerged capabilities of large language models, and the potential ways of making use of large language models for personalization.

References in corpus (21)

• Training language models to follow instructions with human feedback
• KGAT: Knowledge Graph Attention Network for Recommendation
• Knowledge Graph Convolutional Networks for Recommender Systems
• TALLRec: An Effective and Efficient Tuning Framework to Align Large Language Model with Recommendation
• Recommender Systems in the Era of Large Language Models (LLMs)
• NPA: Neural News Recommendation with Personalized Attention
• SHINE: Signed Heterogeneous Information Network Embedding for Sentiment Link Prediction
• Neural Rating Regression with Abstractive Tips Generation for Recommendation
• Estimation-Action-Reflection: Towards Deep Interaction Between Conversational and Recommender Systems
• Uncovering ChatGPT's Capabilities in Recommender Systems
• Interactive Path Reasoning on Graph for Conversational Recommendation
• Rethinking the Evaluation for Conversational Recommendation in the Era of Large Language Models
• Towards Automated Neural Interaction Discovery for Click-Through Rate Prediction
• NRPA: Neural Recommendation with Personalized Attention
• PTM4Tag: Sharpening Tag Recommendation of Stack Overflow Posts with Pre-trained Models
• Exploring Adapter-based Transfer Learning for Recommender Systems: Empirical Studies and Practical Insights
• LLMatic: Neural Architecture Search via Large Language Models and Quality Diversity Optimization
• RecExplainer: Aligning Large Language Models for Explaining Recommendation Models
• Ad Headline Generation using Self-Critical Masked Language Model
• GPT-NAS: Evolutionary Neural Architecture Search with the Generative Pre-Trained Model
• COBART: Controlled, Optimized, Bidirectional and Auto-Regressive Transformer for Ad Headline Generation

Cited by in corpus (11)

• Mapping Student-AI Interaction Dynamics in Multi-Agent Learning Environments: Supporting Personalised Learning and Reducing Performance Gaps
• Ontology in Hybrid Intelligence: a concise literature review
• SmartLLMSentry: A Comprehensive LLM Based Smart Contract Vulnerability Detection Framework
• Comprehending Knowledge Graphs with Large Language Models for Recommender Systems
• From Prediction to Explanation: Multimodal, Explainable, and Interactive Deepfake Detection Framework for Non-Expert Users
• Evaluating the capability of large language models to personalize science texts for diverse middle-school-age learners
• Just Ask for Music (JAM): Multimodal and Personalized Natural Language Music Recommendation
• X-Cross: Dynamic Integration of Language Models for Cross-Domain Sequential Recommendation
• Scene-Aware Memory Discrimination: Deciding Which Personal Knowledge Stays
• Matching Game Preferences Through Dialogical Large Language Models: A Perspective
• Never say never: Exploring the effects of available knowledge on agent persuasiveness in controlled physiotherapy motivation dialogues