Enhancing Conversational Recommender Systems with Tree-Structured Knowledge and Pretrained Language Models

2025/11/16 by Chao Wang, Ren, Yongwen, Peng Du +8
Computer Science · #Topic Modeling #Multimodal Machine Learning Applications #Recommender Systems and Techniques

paper · pdf · doi:10.48550/arxiv.2511.12579

Abstract

Recent advances in pretrained language models (PLMs) have significantly improved conversational recommender systems (CRS), enabling more fluent and context-aware interactions. To further enhance accuracy and mitigate hallucination, many methods integrate PLMs with knowledge graphs (KGs), but face key challenges: failing to fully exploit PLM reasoning over graph relationships, indiscriminately incorporating retrieved knowledge without context filtering, and neglecting collaborative preferences in multi-turn dialogues. To this end, we propose PCRS-TKA, a prompt-based framework employing retrieval-augmented generation to integrate PLMs with KGs. PCRS-TKA constructs dialogue-specific knowledge trees from KGs and serializes them into texts, enabling structure-aware reasoning while capturing rich entity semantics. Our approach selectively filters context-relevant knowledge and explicitly models collaborative preferences using specialized supervision signals. A semantic alignment module harmonizes heterogeneous inputs, reducing noise and enhancing accuracy. Extensive experiments demonstrate that PCRS-TKA consistently outperforms all baselines in both recommendation and conversational quality.

Citations

• A Comprehensive Survey on Self-Interpretable Neural Networks
• MoVA: Adapting Mixture of Vision Experts to Multimodal Context
• Graph Signal Diffusion Model for Collaborative Filtering
• TREA: Tree-Structure Reasoning Schema for Conversational Recommendation
• BARCOR: Towards A Unified Framework for Conversational Recommendation Systems
• C2-CRS: Coarse-to-Fine Contrastive Learning for Conversational Recommender System
• RevCore: Review-augmented Conversational Recommendation
• Empowering News Recommendation with Pre-trained Language Models
• Towards Topic-Guided Conversational Recommender System
• INSPIRED: Toward Sociable Recommendation Dialog Systems
• It's Not Just Size That Matters: Small Language Models Are Also Few-Shot\n Learners
• Improving Conversational Recommender Systems via Knowledge Graph based Semantic Fusion
• Inducing Relational Knowledge from BERT
• BART: Denoising Sequence-to-Sequence Pre-training for Natural Language\n Generation, Translation, and Comprehension
• Language Models as Knowledge Bases?
• Towards Knowledge-Based Recommender Dialog System
• Towards Deep Conversational Recommendations
• Noise Contrastive Estimation and Negative Sampling for Conditional Models: Consistency and Statistical Efficiency
• Self-Attentive Sequential Recommendation
• Modeling Relational Data with Graph Convolutional Networks
• Small Language Models (SLMs) Can Still Pack a Punch: A survey
• BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

Related

• Reasoning over User Preferences: Knowledge Graph-Augmented LLMs for Explainable Conversational Recommendations
• STEP: Stepwise Curriculum Learning for Context-Knowledge Fusion in Conversational Recommendation
• Improving Conversational Recommender Systems via Knowledge Graph based Semantic Fusion
• CR-Walker: Tree-Structured Graph Reasoning and Dialog Acts for Conversational Recommendation
• Graph Retrieval-Augmented LLM for Conversational Recommendation Systems