MM-MoralBench: 一种多模态道德评估基准用于大型视觉-语言模型
MM-MoralBench: A MultiModal Moral Evaluation Benchmark for Large Vision-Language Models
AI总结：
为评估大型视觉-语言模型的道德对齐性，提出MM-MoralBench基准，通过多模态场景测试模型在六个道德基础上的判断与分类能力，揭示模型存在显著的道德偏见问题。
摘要：
大型视觉-语言模型（LVLMs）在关键领域快速整合，需要全面的道德评估以确保其与人类价值观一致。尽管已有大量研究探讨LLMs的道德评估，但文本中心的评估无法充分捕捉视觉模态引入的复杂上下文和模糊性。为此，我们引入MM-MoralBench，一种基于道德基础理论的多模态道德评估基准。我们通过合成视觉上下文与角色对话结合，构建独特的多模态场景，模拟现实世界中视觉和语言信息动态交互的困境。该基准通过道德判断、分类和响应任务评估模型在六个道德基础上的表现。对超过20个LVLMs的广泛评估表明，模型表现出显著的道德对齐偏差，与人类共识显著偏离。进一步分析显示，通用扩展或结构改进在道德对齐上收效甚微，而思维范式可能在道德情境中引发过度思考失败，凸显了针对性道德对齐策略的必要性。本基准已公开发布。
英文摘要：
The rapid integration of Large Vision-Language Models (LVLMs) into critical domains necessitates comprehensive moral evaluation to ensure their alignment with human values. While extensive research has addressed moral evaluation in LLMs, text-centric assessments cannot adequately capture the complex contextual nuances and ambiguities introduced by visual modalities. To bridge this gap, we introduce MM-MoralBench, a multimodal moral evaluation benchmark grounded in Moral Foundations Theory. We construct unique multimodal scenarios by combining synthesized visual contexts with character dialogues to simulate real-world dilemmas where visual and linguistic information interact dynamically. Our benchmark assesses models across six moral foundations through moral judgment, classification, and response tasks. Extensive evaluations of over 20 LVLMs reveal that models exhibit pronounced moral alignment bias, diverging significantly from human consensus. Furthermore, our analysis indicates that general scaling or structural improvements yield diminishing returns in moral alignment, and thinking paradigm may trigger overthinking-induced failures in moral contexts, highlighting the necessity for targeted moral alignment strategies. Our benchmark is publicly available.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
