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

TL;DR

This paper introduces PCRS-TKA, a prompt-based framework that enhances conversational recommender systems by integrating knowledge graphs with pretrained language models through structured knowledge trees and selective filtering, improving accuracy and coherence.

Contribution

The paper presents a novel retrieval-augmented generation framework that constructs dialogue-specific knowledge trees and models collaborative preferences, addressing key limitations of previous methods.

Findings

PCRS-TKA outperforms baselines in recommendation accuracy.

The structured knowledge trees improve reasoning over graph relationships.

Selective knowledge filtering reduces noise and enhances conversational quality.

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.