MM-THEBench: 多模态大语言模型是否能合理推理？
MM-THEBench: Do Reasoning MLLMs Think Reasonably?
AI总结：
MM-THEBench旨在评估推理MLLMs在中间推理过程中的幻觉问题，通过细粒度分类和多层次评估框架，揭示思考对多模态任务中幻觉和推理能力的影响。
摘要：
多模态大语言模型（MLLMs）的最新进展标志着从非思考模型向经过训练的推理模型的转变，后者能够通过思考解决复杂问题。然而，这种思考是否能减轻多模态感知和推理中的幻觉现象仍不明确。自我反思推理虽然增强了鲁棒性，但会引入额外的幻觉，细微的感知错误仍导致错误或偶然正确的答案。现有基准测试主要关注在推理MLLMs出现之前模型，忽略了内部思考过程，未能衡量思考过程中产生的幻觉。为了解决这些挑战，我们引入MM-THEBench，一个用于评估推理MLLMs中间CoTs幻觉的综合性基准测试。MM-THEBench具有基于认知维度的细粒度分类体系、多样化的数据集以及经过验证的推理注释，以及多层次的自动化评估框架。对主流推理MLLMs的广泛实验揭示了思考如何影响各种多模态任务中的幻觉和推理能力。
英文摘要：
Recent advances in multimodal large language models (MLLMs) mark a shift from non-thinking models to post-trained reasoning models capable of solving complex problems through thinking. However, whether such thinking mitigates hallucinations in multimodal perception and reasoning remains unclear. Self-reflective reasoning enhances robustness but introduces additional hallucinations, and subtle perceptual errors still result in incorrect or coincidentally correct answers. Existing benchmarks primarily focus on models before the emergence of reasoning MLLMs, neglecting the internal thinking process and failing to measure the hallucinations that occur during thinking. To address these challenges, we introduce MM-THEBench, a comprehensive benchmark for assessing hallucinations of intermediate CoTs in reasoning MLLMs. MM-THEBench features a fine-grained taxonomy grounded in cognitive dimensions, diverse data with verified reasoning annotations, and a multi-level automated evaluation framework. Extensive experiments on mainstream reasoning MLLMs reveal insights into how thinking affects hallucination and reasoning capability in various multimodal tasks.
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。
