Logic-Scaffolding: Personalized Aspect-Instructed Recommendation Explanation Generation using LLMs
This addresses the need for more reliable personalized explanation generation in recommendation systems, though it appears incremental as it builds on existing prompting techniques.
The paper tackles the problem of unreliable zero-shot explanation generation for recommendations using LLMs by proposing Logic-Scaffolding, a framework that combines aspect-based explanation and chain-of-thought prompting to improve reliability through intermediate reasoning steps.
The unique capabilities of Large Language Models (LLMs), such as the natural language text generation ability, position them as strong candidates for providing explanation for recommendations. However, despite the size of the LLM, most existing models struggle to produce zero-shot explanations reliably. To address this issue, we propose a framework called Logic-Scaffolding, that combines the ideas of aspect-based explanation and chain-of-thought prompting to generate explanations through intermediate reasoning steps. In this paper, we share our experience in building the framework and present an interactive demonstration for exploring our results.