CoLLM: Integrating Collaborative Embeddings Into Large Language Models for Recommendation

2025/02/12 by Yang Zhang, Fuli Feng, Jizhi Zhang +3 · 14 citations
Computer Science · #Machine Learning in Healthcare #Recommender Systems and Techniques #Topic Modeling

paper · doi:10.1109/tkde.2025.3540912

openalex publication_date 2025/02/12 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/29

Abstract

Leveraging Large Language Models as recommenders, referred to as LLMRec, is gaining traction and brings novel dynamics for modeling user preferences, particularly for cold-start users. However, existing LLMRec approaches primarily focus on text semantics and overlook the crucial aspect of incorporating collaborative information from user-item interactions, leading to potentially sub-optimal performance in warm-start scenarios. To ensure superior recommendations across both warm and cold scenarios, we introduceCoLLM, an innovative LLMRec approach that explicitly integrates collaborative information for recommendations. CoLLM treats collaborative information as a distinct modality, directly encoding it from well-established traditional collaborative models, and then tunes a mapping module to align this collaborative information with the LLM's input text token space for recommendations. By externally integrating traditional models, CoLLM ensures effective collaborative information modeling without modifying the LLM itself, providing the flexibility to adopt diverse collaborative information modeling mechanisms. Extensive experimentation validates that CoLLM adeptly integrates collaborative information into LLMs, resulting in enhanced recommendation performance.

Citations

• Matrix Factorization Techniques for Recommender Systems
• LightGCN
• Large language models encode clinical knowledge

Cited by

• Think before Recommendation: Autonomous Reasoning-enhanced Recommender
• Bi-Level Optimization for Generative Recommendation: Bridging Tokenization and Generation
• Rank-GRPO: Training LLM-based Conversational Recommender Systems with Reinforcement Learning
• Reinforced Preference Optimization for Recommendation
• Leveraging Language Semantics for Collaborative Filtering with TextGCN and TextGCN-MLP: Zero-Shot vs In-Domain Performance
• Reinforced Strategy Optimization for Conversational Recommender Systems via Network-of-Experts
• Restoring Collaborative Signals in Semantic-ID Generative Recommendation via Personalized Natural Language
• Hierarchical Latent Reasoning for LLM-based Recommendation
• Membership Inference Attack against Large Language Model-based Recommendation Systems: A New Distillation-based Paradigm
• Decoding in Latent Spaces for Efficient Inference in LLM-based Recommendation
• RecMind: LLM-Enhanced Graph Neural Networks for Personalized Consumer Recommendations
• TrackRec: Iterative Alternating Feedback with Chain-of-Thought via Preference Alignment for Recommendation
• Beyond Single Labels: Improving Conversational Recommendation through LLM-Powered Data Augmentation
• Latent Inter-User Difference Modeling for LLM Personalization

Related

• CoLLM: Integrating Collaborative Embeddings into Large Language Models for Recommendation
• CoRA: Collaborative Information Perception by Large Language Model's Weights for Recommendation
• Large Language Models meet Collaborative Filtering: An Efficient All-round LLM-based Recommender System
• Text-like Encoding of Collaborative Information in Large Language Models for Recommendation
• Enhancing LLM-based Recommendation through Semantic-Aligned Collaborative Knowledge