User Preferences for Large Language Model versus Template-Based Explanations of Movie Recommendations: A Pilot Study

TL;DR

This pilot study explores the use of large language models to generate more engaging and personalized explanations for movie recommendations, comparing them to traditional template-based methods.

Contribution

It introduces a novel LLM-based explanation approach and evaluates its potential to enhance user experience in recommender systems.

Findings

LLM-based explanations may be more engaging and resonant.

Participants showed high variance in preferences for explanation types.

Preliminary results indicate potential for improved user satisfaction.

Abstract

Recommender systems have become integral to our digital experiences, from online shopping to streaming platforms. Still, the rationale behind their suggestions often remains opaque to users. While some systems employ a graph-based approach, offering inherent explainability through paths associating recommended items and seed items, non-experts could not easily understand these explanations. A popular alternative is to convert graph-based explanations into textual ones using a template and an algorithm, which we denote here as ''template-based'' explanations. Yet, these can sometimes come across as impersonal or uninspiring. A novel method would be to employ large language models (LLMs) for this purpose, which we denote as ''LLM-based''. To assess the effectiveness of LLMs in generating more resonant explanations, we conducted a pilot study with 25 participants. They were presented with three explanations: (1) traditional template-based, (2) LLM-based rephrasing of the template output, and (3) purely LLM-based explanations derived from the graph-based explanations. Although subject to high variance, preliminary findings suggest that LLM-based explanations may provide a richer and more engaging user experience, further aligning with user expectations. This study sheds light on the potential limitations of current explanation methods and offers promising directions for leveraging large language models to improve user satisfaction and trust in recommender systems.