From Reasoning Depth to Reasoning Breadth: Evaluating Multi-Point Associative Reasoning in Large Language Models
从推理深度到推理广度:评估大型语言模型中的多点关联推理
机构 * Beijing University of Posts and Telecommunications(北京邮电大学) ; Peking University(北京大学) ; Kuaishou Technology(快手科技)
AI总结 该研究构建了中英双语多点关联推理基准MPAR-Bench,发现大型语言模型的推理深度未自动带来稳健的推理广度,当前基准未充分覆盖推理广度。