RDRec: Rationale Distillation for LLM-based Recommendation
This work addresses the need for more interpretable and effective recommendations in AI systems, though it appears incremental as it builds on existing LLM-based methods by adding rationale distillation.
The paper tackles the problem of limited reasoning capability in LLM-based recommender models by proposing RDRec, a compact model that learns rationales from a larger language model to specify user and item profiles, achieving state-of-the-art performance in top-N and sequential recommendations.
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.