HELM: A Human-Centered Evaluation Framework for LLM-Powered Recommender Systems

TL;DR

This paper introduces HELM, a comprehensive human-centered evaluation framework for LLM-powered recommender systems, assessing multiple qualitative dimensions beyond traditional accuracy metrics to better capture user experience.

Contribution

It presents HELM, a novel evaluation framework that systematically measures human-centered qualities of LLM-based recommenders across five key dimensions.

Findings

GPT-4 has the highest explanation quality and interaction naturalness.

GPT-4 shows significant popularity bias compared to traditional methods.

HELM reveals critical quality aspects invisible to traditional metrics.

Abstract

The integration of Large Language Models (LLMs) into recommendation systems has introduced unprecedented capabilities for natural language understanding, explanation generation, and conversational interactions. However, existing evaluation methodologies focus predominantly on traditional accuracy metrics, failing to capture the multifaceted human-centered qualities that determine the real-world user experience. We introduce \framework{} (\textbf{H}uman-centered \textbf{E}valuation for \textbf{L}LM-powered reco\textbf{M}menders), a comprehensive evaluation framework that systematically assesses LLM-powered recommender systems across five human-centered dimensions: \textit{Intent Alignment}, \textit{Explanation Quality}, \textit{Interaction Naturalness}, \textit{Trust \& Transparency}, and \textit{Fairness \& Diversity}. Through extensive experiments involving three state-of-the-art LLM-based recommenders (GPT-4, LLaMA-3.1, and P5) across three domains (movies, books, and restaurants), and rigorous evaluation by 12 domain experts using 847 recommendation scenarios, we demonstrate that \framework{} reveals critical quality dimensions invisible to traditional metrics. Our results show that while GPT-4 achieves superior explanation quality (4.21/5.0) and interaction naturalness (4.35/5.0), it exhibits a significant popularity bias (Gini coefficient 0.73) compared to traditional collaborative filtering (0.58). We release \framework{} as an open-source toolkit to advance human-centered evaluation practices in the recommender systems community.