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

2025-11-16

AI Summary

Existing conversational recommendation systems struggle to effectively leverage pretrained language models (PLMs) for relational reasoning, contextual knowledge filtering, and multi-turn collaborative preference modeling, leading to hallucination and degraded recommendation and dialogue quality. To address these challenges, we propose PCRS-TKA—a Prompt-driven Conversational Recommendation System with Tree-structured Knowledge Alignment. Our method constructs a dialogue-specific knowledge tree to enable structure-aware relational reasoning; designs selective knowledge filtering and explicit collaborative preference modeling; integrates knowledge graph sequence representations with PLM latent spaces via a semantic alignment module; and employs prompt-driven retrieval-augmented generation. Evaluated on multiple benchmarks, PCRS-TKA achieves significant improvements in recommendation accuracy (Recall@10 ↑12.3%) and dialogue coherence (BLEU-4 ↑8.7%), demonstrating strong robustness and substantially mitigating hallucination.

Technology Category

• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Knowledge Representation and Reasoning: Preferences
• Natural Language Processing: Conversational AI/Dialog Systems

Application Category

• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Search and Retrieval-Augmented AI: Assisted, interactive, and conversational search
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

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.

Problem

• Enhancing reasoning over knowledge graph relationships in conversational recommenders
• Filtering irrelevant retrieved knowledge to reduce hallucination
• Modeling collaborative preferences in multi-turn dialogue systems

Innovation

• Constructs dialogue-specific knowledge trees from KGs
• Selectively filters context-relevant knowledge with supervision
• Aligns semantic inputs to reduce noise and enhance accuracy