摘要
针对灾害响应中需在低空无人机噪声视图及边缘计算受限下完成多阶段推理的挑战，本文提出 DisasterBench，一个涵盖 14 种场景与 9 项关键任务的多模态推理基准，重点测试因果归因、传播预测及决策推理。此外，作者推出轻量级模型 DisasterVL，采用包含思维链引导对齐的三阶段优化流程。实验表明，该 2B 参数模型在推理精度上媲美 GPT-4o，且效率更优，显著缩小了开源与闭源模型的差距。
AI 推荐理由
论文核心构建多阶段推理基准，并提出思维链引导的对齐方法，专注提升复杂环境下的因果与决策推理能力。
研究机构
School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, 611731, China
School of Information and Communication Engineering, Dalian University of Technology, Dalian, 116024, China
School of Computing and Communications, Lancaster University, Lancaster, LA1 4YW, England
School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, 430074, China
论文信息