Towards Unified Conversational Recommender Systems via Knowledge-Enhanced Prompt Learning

Abstract

Conversational recommender systems (CRS) aim to proactively elicit user preference and recommend high-quality items through natural language conversations. Typically, a CRS consists of a recommendation module to predict preferred items for users and a conversation module to generate appropriate responses. To develop an effective CRS, it is essential to seamlessly integrate the two modules. Existing works either design semantic alignment strategies, or share knowledge resources and representations between the two modules. However, these approaches still rely on different architectures or techniques to develop the two modules, making it difficult for effective module integration. To address this problem, we propose a unified CRS model named UniCRS based on knowledge-enhanced prompt learning. Our approach unifies the recommendation and conversation subtasks into the prompt learning paradigm, and utilizes knowledge-enhanced prompts based on a fixed pre-trained language model (PLM) to fulfill both subtasks in a unified approach. In the prompt design, we include fused knowledge representations, task-specific soft tokens, and the dialogue context, which can provide sufficient contextual information to adapt the PLM for the CRS task. Besides, for the recommendation subtask, we also incorporate the generated response template as an important part of the prompt, to enhance the information interaction between the two subtasks. Extensive experiments on two public CRS datasets have demonstrated the effectiveness of our approach.

Accepted by KDD 2022. Code: https://github.com/RUCAIBox/UniCRS

References in corpus (2)

• Advances and Challenges in Conversational Recommender Systems: A Survey
• Leveraging Historical Interaction Data for Improving Conversational Recommender System

Cited by in corpus (17)

• Recommender Systems in the Era of Large Language Models (LLMs)
• When Large Language Models Meet Personalization: Perspectives of Challenges and Opportunities
• Large Language Models as Zero-Shot Conversational Recommenders
• Rethinking the Evaluation for Conversational Recommendation in the Era of Large Language Models
• Variational Reasoning over Incomplete Knowledge Graphs for Conversational Recommendation
• Exploring Adapter-based Transfer Learning for Recommender Systems: Empirical Studies and Practical Insights
• Knowledge Graphs and Pre-trained Language Models enhanced Representation Learning for Conversational Recommender Systems
• Behavior Alignment: A New Perspective of Evaluating LLM-based Conversational Recommender Systems
• Towards Empathetic Conversational Recommender Systems
• Knowledge-Enhanced Conversational Recommendation via Transformer-based Sequential Modelling
• RecUserSim: A Realistic and Diverse User Simulator for Evaluating Conversational Recommender Systems
• Towards Building Voice-based Conversational Recommender Systems: Datasets, Potential Solutions, and Prospects
• MSCRS: Multi-modal Semantic Graph Prompt Learning Framework for Conversational Recommender Systems
• Bayesian Optimization with LLM-Based Acquisition Functions for Natural Language Preference Elicitation
• CRS Arena: Crowdsourced Benchmarking of Conversational Recommender Systems
• STEP: Stepwise Curriculum Learning for Context-Knowledge Fusion in Conversational Recommendation
• Improving Conversational Recommendation with Contextual Adaptation of External Recommenders and LLM-based Reranking