SOURCE-LINKED INTELLIGENCE

Quantifying and Mitigating Korean Jamo-Level Typographical Vulnerabilities in Large Language Models

arXiv · AI, language, vision and robotics · article · Aug 31, 2026 · UTC

Korean introduces an additional typographical perturbation level not captured by ordinary character-level edit models: because syllable blocks are internally composed of sub-character units called jamo, keyboard-level errors can occur within a syllable, either producing a valid but semantically altered character or exposing raw jamo on the surface. Both outcomes disrupt sub-word tokenization and are not reliably corrected by existing grammatical error correction pipelines, leaving LLMs directly exposed to corrupted inputs. To quantify this vulnerability, we apply five jamo-level perturbation t

Read original source ↗ Open in workspace

recordType

paper

region

Global