Generative Conversational Recommender System

TL;DR

This paper introduces a fully generative conversational recommender system that unifies recommendation and dialogue generation within a single autoregressive framework, improving recommendation accuracy and coherence.

Contribution

It proposes a novel integrated generative model that jointly predicts items and responses, with a structured decision process for more coherent and faithful recommendations.

Findings

Achieves up to 29% improvement in Recall@1 over baselines.

Enables end-to-end training for recommendation and dialogue.

Maintains competitive dialogue quality while enhancing recommendation performance.

Abstract

Conversational recommender systems aim to provide personalized recommendations via natural language interactions. However, existing approaches either decouple recommendation from dialog generation or rely on retrieval-based pipelines, limiting the integration between recommendation and response generation and leading to suboptimal modeling of user intent. In this paper, we propose a fully generative conversational recommender system that unifies recommendation and dialog generation within a single autoregressive framework. Our approach represents items as discrete semantic IDs and integrates them directly into the generation process, enabling joint prediction of items and responses via next-token modeling. We further introduce a structured generation paradigm that factorizes conversational recommendation into a sequence of interdependent decisions, where the model first predicts the response intent and the recommendation target, and then generates the response conditioned on them. This design enables end-to-end optimization, enforces a more coherent dependency structure, and supports faithful item generation via constrained decoding. Extensive experiments demonstrate that our method consistently improves recommendation performance, achieving gains of up to 29% on Recall@1 over strong baselines, while maintaining competitive dialog quality.