Towards LLM-Enhanced Group Recommender Systems

TL;DR

This paper explores how large language models can enhance group recommender systems by addressing group dynamics, decision-making, and explanation generation to improve recommendation quality and applicability.

Contribution

It analyzes the potential of LLMs to support complex group recommendation tasks, focusing on understanding group behavior and providing explanations.

Findings

LLMs can model group dynamics effectively

LLMs improve explanation quality for group recommendations

Potential for increased decision support in group settings

Abstract

In contrast to single-user recommender systems, group recommender systems are designed to generate and explain recommendations for groups. This group-oriented setting introduces additional complexities, as several factors - absent in individual contexts - must be addressed. These include understanding group dynamics (e.g., social dependencies within the group), defining effective decision-making processes, ensuring that recommendations are suitable for all group members, and providing group-level explanations as well as explanations for individual users. In this paper, we analyze in which way large language models (LLMs) can support these aspects and help to increase the overall decision support quality and applicability of group recommender systems.