Politeness Stereotypes and Attack Vectors: Gender Stereotypes in Japanese and Korean Language Models
This work addresses gender bias in non-English language models, highlighting risks in cyberbullying detection, but is incremental as it extends existing bias research to specific languages.
The study investigated gender bias in Japanese and Korean language models, finding that informal polite speech is associated with female grammatical gender and rude/formal speech with male grammatical gender, and that politeness levels can be exploited to bypass cyberbullying detection models, with training on a proposed dataset mitigating these biases.
In efforts to keep up with the rapid progress and use of large language models, gender bias research is becoming more prevalent in NLP. Non-English bias research, however, is still in its infancy with most work focusing on English. In our work, we study how grammatical gender bias relating to politeness levels manifests in Japanese and Korean language models. Linguistic studies in these languages have identified a connection between gender bias and politeness levels, however it is not yet known if language models reproduce these biases. We analyze relative prediction probabilities of the male and female grammatical genders using templates and find that informal polite speech is most indicative of the female grammatical gender, while rude and formal speech is most indicative of the male grammatical gender. Further, we find politeness levels to be an attack vector for allocational gender bias in cyberbullying detection models. Cyberbullies can evade detection through simple techniques abusing politeness levels. We introduce an attack dataset to (i) identify representational gender bias across politeness levels, (ii) demonstrate how gender biases can be abused to bypass cyberbullying detection models and (iii) show that allocational biases can be mitigated via training on our proposed dataset. Through our findings we highlight the importance of bias research moving beyond its current English-centrism.