Assessment of Multimodal Large Language Models in Alignment with Human Values

TL;DR

This paper introduces Ch3Ef, a comprehensive dataset and evaluation strategy to assess how well Multimodal Large Language Models align with human values across diverse tasks and domains.

Contribution

The paper presents the Ch3Ef dataset and a unified evaluation strategy specifically designed for assessing MLLMs' alignment with human values in visual and multimodal contexts.

Findings

MLLMs show varied alignment with human values across domains.

Evaluation reveals specific strengths and limitations of current MLLMs.

Guidelines for future improvements in MLLM alignment are proposed.

Abstract

Large Language Models (LLMs) aim to serve as versatile assistants aligned with human values, as defined by the principles of being helpful, honest, and harmless (hhh). However, in terms of Multimodal Large Language Models (MLLMs), despite their commendable performance in perception and reasoning tasks, their alignment with human values remains largely unexplored, given the complexity of defining hhh dimensions in the visual world and the difficulty in collecting relevant data that accurately mirrors real-world situations. To address this gap, we introduce Ch3Ef, a Compreh3ensive Evaluation dataset and strategy for assessing alignment with human expectations. Ch3Ef dataset contains 1002 human-annotated data samples, covering 12 domains and 46 tasks based on the hhh principle. We also present a unified evaluation strategy supporting assessment across various scenarios and different perspectives. Based on the evaluation results, we summarize over 10 key findings that deepen the understanding of MLLM capabilities, limitations, and the dynamic relationships between evaluation levels, guiding future advancements in the field.