Understanding the Ability of LLMs to Handle Character-Level Perturbation 事件

Understanding the Ability of LLMs to Handle Character-Level Perturbation arXiv:2510.14365v4 Announce Type: replace Abstract: This work investigates the resilience of contemporary large language models (LLMs) against frequent character-level perturbations. We examine three types of character-level perturbations including introducing numerous typos within words, shuffling the characters in each word, and inserting a large number of invisible characters into the text. Surprisingly, even under seve