RDRec: Rationale Distillation for LLM-based Recommendation

TL;DR

This paper introduces RDRec, a compact recommender model that distills rationales from large language models to improve recommendation accuracy by leveraging user and item review data.

Contribution

The paper presents a novel rationale distillation approach for LLM-based recommenders, enhancing their reasoning by explicitly modeling rationales from reviews.

Findings

RDRec achieves state-of-the-art performance in top-N recommendations.

The model effectively captures user preferences and item attributes.

Rationale distillation improves recommendation interpretability.

Abstract

Large language model (LLM)-based recommender models that bridge users and items through textual prompts for effective semantic reasoning have gained considerable attention. However, few methods consider the underlying rationales behind interactions, such as user preferences and item attributes, limiting the reasoning capability of LLMs for recommendations. This paper proposes a rationale distillation recommender (RDRec), a compact model designed to learn rationales generated by a larger language model (LM). By leveraging rationales from reviews related to users and items, RDRec remarkably specifies their profiles for recommendations. Experiments show that RDRec achieves state-of-the-art (SOTA) performance in both top-N and sequential recommendations. Our source code is released at https://github.com/WangXFng/RDRec.