作者位次 #3/11ACL 2026Poster· Natural Language Processing
D is C al: Distribution-Aware Calibration for Mathematical Reasoning Under Character-Level Noisy Inputs
Bo Zhang · Jiawei Zhang · Cong Gao · Bingxu Han · Minghao Hu · Jun Zhang · Yunbo Cao · Zhunchen Luo · Wen Yao · Guotong Geng · Zhong Wang
摘要
Although large reasoning models (LRMs) exhibit exceptional mathematical reasoning capabilities on clean inputs, their reasoning accuracy drops substantially in the presence of character-level noise such as typographical errors. Critically, their confidence estimates fail to reflect the correspond...