Beyond Single Labels: Improving Conversational Recommendation through LLM-Powered Data Augmentation

TL;DR

This paper introduces a novel LLM-powered data augmentation framework for conversational recommender systems, improving recommendation accuracy by balancing semantic relevance and collaborative information.

Contribution

It proposes a two-stage data augmentation and training strategy leveraging LLMs to enhance CRS performance, addressing false negatives and data noise issues.

Findings

Significant performance improvements on benchmark datasets.

Effective balancing of semantic relevance and collaborative signals.

Robustness demonstrated across multiple recommender models.

Abstract

Conversational recommender systems (CRSs) enhance recommendation quality by engaging users in multi-turn dialogues, capturing nuanced preferences through natural language interactions. However, these systems often face the false negative issue, where items that a user might like are incorrectly labeled as negative during training, leading to suboptimal recommendations.Expanding the label set through data augmentation presents an intuitive solution but faces the challenge of balancing two key aspects: ensuring semantic relevance and preserving the collaborative information inherent in CRS datasets. To address these issues, we propose a novel data augmentation framework that first leverages an LLM-based semantic retriever to identify diverse and semantically relevant items, which are then filtered by a relevance scorer to remove noisy candidates. Building on this, we introduce a two-stage training strategy balancing semantic relevance and collaborative information. Extensive experiments on two benchmark datasets and user simulators demonstrate significant and consistent performance improvements across various recommenders, highlighting the effectiveness of our approach in advancing CRS performance.