Obfuscation Rules for Detecting and Detoxifying Korean Toxicity
Quick summary
arXiv:2510.10961v4 Announce Type: replace-cross Abstract: As language models become increasingly deployed in online environments, toxicity detection and detoxification have received growing attention. Existing studies primarily focus on non-obfuscated text, which limits robustness when users intentionally disguise toxic expressions. In particular, Korean toxic expressions can be easily disguised through agglutinative morphology and Hangeul-specific orthographic variation. However, obfuscation in Korean remains largely unexplored, which motivates us to introduce a KOTOX: Korean toxic dataset fo
Key takeaways
- arXiv:2510.10961v4 Announce Type: replace-cross Abstract: As language models become increasingly deployed in online environments, toxicity detection and detoxification have received growing attention.
- Existing studies primarily focus on non-obfuscated text, which limits robustness when users intentionally disguise toxic expressions.
- In particular, Korean toxic expressions can be easily disguised through agglutinative morphology and Hangeul-specific orthographic variation.
Why it matters
The importance of “Obfuscation Rules for Detecting and Detoxifying Korean Toxicity” will be measured by what changes in practice. User behavior, access conditions, verifiable performance and responsible-use outcomes are the signals worth following.
Member comments