MAPLE: Enhancing Review Generation with Multi-Aspect Prompt LEarning in Explainable Recommendation

2024-08-19

arXiv.org

AI Summary

Existing explainable recommendation systems suffer from weak generalizability, factual hallucinations, and non-personalized explanations in review generation. To address these issues, we propose Multi-Aspect Prompt Learning (MAPL), a novel framework that explicitly incorporates fine-grained aspect categories as prompts to strengthen aspect-term memorization and controllability. MAPL innovatively integrates a lightweight prompt model with a large language model (LLM) to construct a retrieval-augmented reading architecture for explainable generation. Extensive experiments on two real-world restaurant-domain datasets demonstrate that MAPL significantly improves the diversity, aspect coverage, and factual relevance of generated explanations. Moreover, the explanations are more personalized, information-rich, and logically coherent. Our code and datasets will be publicly released.

Technology Category

• Natural Language Processing: Generation
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Explainable Recommendation task is designed to receive a pair of user and item and output explanations to justify why an item is recommended to a user. Many models treat review-generation as a proxy of explainable recommendation. Although they are able to generate fluent and grammatical sentences, they suffer from generality and hallucination issues. We propose a personalized, aspect-controlled model called Multi-Aspect Prompt LEarner (MAPLE), in which it integrates aspect category as another input dimension to facilitate the memorization of fine-grained aspect terms. Experiments on two real-world review datasets in restaurant domain show that MAPLE outperforms the baseline review-generation models in terms of text and feature diversity while maintaining excellent coherence and factual relevance. We further treat MAPLE as a retriever component in the retriever-reader framework and employ a Large-Language Model (LLM) as the reader, showing that MAPLE's explanation along with the LLM's comprehension ability leads to enriched and personalized explanation as a result. We will release the code and data in this http upon acceptance.

Problem

• Improving personalized aspect-controlled review generation
• Enhancing diversity and coverage of recommendation aspects
• Ensuring coherence and factual relevance in explanations

Innovation

• Multi-aspect prompt learning for personalized recommendations
• Aspect-controlled model enhancing review generation
• Improves diversity and coherence in generated content