Cold-Start Recommendation towards the Era of Large Language Models (LLMs): A Comprehensive Survey and Roadmap

2025-01-03

AI Summary

This paper addresses the cold-start recommendation problem empowered by large language models (LLMs). Methodologically, it establishes the first comprehensive landscape and unified taxonomy for LLM-driven cold-start recommendation, proposing a “knowledge integration evolution roadmap” that formalizes three novel paradigms: semantic understanding, external knowledge injection, and cross-modal alignment. It integrates LLMs with graph neural networks, cross-domain transfer learning, prompt engineering, and knowledge distillation to construct a multi-source heterogeneous information modeling framework. Contributions include: (1) an authoritative survey covering over 100 works; (2) an open-source resource repository (GitHub) featuring curated datasets, models, and prompts; (3) a reproducible benchmark with standardized evaluation protocols; and (4) an open toolchain and research roadmap. Collectively, these advances provide both theoretical foundations and practical guidelines for researchers and practitioners in academia and industry.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: (Large) Language Models
• Data Mining & Knowledge Management: Recommender Systems

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Cold-start problem is one of the long-standing challenges in recommender systems, focusing on accurately modeling new or interaction-limited users or items to provide better recommendations. Due to the diversification of internet platforms and the exponential growth of users and items, the importance of cold-start recommendation (CSR) is becoming increasingly evident. At the same time, large language models (LLMs) have achieved tremendous success and possess strong capabilities in modeling user and item information, providing new potential for cold-start recommendations. However, the research community on CSR still lacks a comprehensive review and reflection in this field. Based on this, in this paper, we stand in the context of the era of large language models and provide a comprehensive review and discussion on the roadmap, related literature, and future directions of CSR. Specifically, we have conducted an exploration of the development path of how existing CSR utilizes information, from content features, graph relations, and domain information, to the world knowledge possessed by large language models, aiming to provide new insights for both the research and industrial communities on CSR. Related resources of cold-start recommendations are collected and continuously updated for the community in https://github.com/YuanchenBei/Awesome-Cold-Start-Recommendation.

Problem

• Recommendation Systems
• Cold Start Problem
• Large Language Models

Innovation

• Cold Start Recommendation
• Large Language Models
• Content-based and Knowledge-based Approaches