作者位次 #4/6ACL 2026Findings· Findings of ACL
GSM -Noise: Exploring and Enhancing Large Language Models’ Reasoning under Noisy Inputs
Zhengxin Zhang · Chengyu Huang · Xufu Liu · Dan Zhao · Jinyan Su · Claire Cardie
摘要
Large language models (LLMs) have demonstrated impressive reasoning capabilities, yet they often struggle when dealing with complex, ill-formed, or noisy inputs that frequently occur in interactions with real users. LLMs typically lack crucial refining capabilities needed to filter out irrelevant...