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

2026-08-31

AI Summary

研究解决了韩语中辅音字母级输入错误对大语言模型的影响问题，通过提出Typo-Aware Chain-of-Thought方法减轻了这种影响。

Abstract

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 types to the KMMLU benchmark and evaluate four language models, finding that accuracy declines monotonically with perturbation intensity and that parameter scaling does not confer robustness against intra-syllabic noise. We further show that typo-corrupted inputs induce a distinct shift in internal representations that is not reducible to ordinary answer incorrectness, and that a simple linear probe trained on these representations detects unseen perturbation types with high AUROC. Motivated by this signal, we propose Typo-Aware Chain-of-Thought (TACoT), which routes inputs to chain-of-thought inference only when the probe detects a likely typo, recovering a substantial portion of the CoT accuracy gain at a fraction of the inference cost.

Problem

• Korean Jamo
• Typographical Vulnerabilities
• Large Language Models
• Syllable-Level Errors
• Input Corruption

Innovation

• jamo-level perturbation
• Typo-Aware Chain-of-Thought
• internal representations
• linear probe