LANE: Logic Alignment of Non-tuning Large Language Models and Online Recommendation Systems for Explainable Reason Generation

TL;DR

This paper introduces LANE, a cost-effective method for aligning large language models with online recommendation systems to generate explainable recommendations without additional model tuning.

Contribution

The proposed LANE strategy aligns LLMs with recommendation systems using semantic embedding and prompting techniques, avoiding costly fine-tuning and enhancing explainability.

Findings

Maintains recommendation performance while improving explainability

Reduces costs by avoiding LLM fine-tuning

Provides coherent and user-aligned recommendations

Abstract

The explainability of recommendation systems is crucial for enhancing user trust and satisfaction. Leveraging large language models (LLMs) offers new opportunities for comprehensive recommendation logic generation. However, in existing related studies, fine-tuning LLM models for recommendation tasks incurs high computational costs and alignment issues with existing systems, limiting the application potential of proven proprietary/closed-source LLM models, such as GPT-4. In this work, our proposed effective strategy LANE aligns LLMs with online recommendation systems without additional LLMs tuning, reducing costs and improving explainability. This innovative approach addresses key challenges in integrating language models with recommendation systems while fully utilizing the capabilities of powerful proprietary models. Specifically, our strategy operates through several key components: semantic embedding, user multi-preference extraction using zero-shot prompting, semantic alignment, and explainable recommendation generation using Chain of Thought (CoT) prompting. By embedding item titles instead of IDs and utilizing multi-head attention mechanisms, our approach aligns the semantic features of user preferences with those of candidate items, ensuring coherent and user-aligned recommendations. Sufficient experimental results including performance comparison, questionnaire voting, and visualization cases prove that our method can not only ensure recommendation performance, but also provide easy-to-understand and reasonable recommendation logic.