Human-Centric Framework for Large Multimodal Models Evaluation
Abstract
Large multimodal models (LMMs) have been widely tested on tasks like visual question answering (VQA), image captioning, and grounding, but lack rigorous evaluation for alignment with human-centered (HC) values such as fairness, ethics, and inclusivity. To address this gap, we introduce \textbf{HumaniBench}, a novel benchmark of 32,000 real-world image-question pairs and an evaluation suite. Labels are generated via an AI-assisted pipeline and validated by experts. HumaniBench assesses LMMs across seven key alignment principles: fairness, ethics, empathy, inclusivity, reasoning, robustness, and multilinguality, through open-ended and closed-ended VQA tasks. Grounded in AI ethics and real-world needs, these principles provide a holistic lens for societal impact. Benchmarking results on different LMM shows that proprietary models generally lead in reasoning, fairness, and multilinguality, while open-source models excel in robustness and grounding. Most models struggle to balance accuracy with ethical and inclusive behavior. HumaniBench offers a rigorous testbed to diagnose limitations, and promote responsible LMM development. Code and data are available for reproducibility.