作者位次 #7/8ACL 2026Poster· Natural Language Processing
Mathematical Proof as a Litmus Test: Revealing Failure Modes of Advanced Large Reasoning Models
Dadi Guo · Jiayu Liu · Zhiyuan Fan · Zhitao He · Haoran Li · Yuxin Li · Yumeng Wang · Yi R. Fung
摘要
Large reasoning models ( e.g., R1, o3) have demonstrated remarkable mathematical problem-solving abilities. However, the high reported accuracy of these advanced models on popular datasets and reliance on purely numerical evaluation often mask their true reasoning shortcomings. To address this, w...