Designing LLMs for cultural sensitivity: Evidence from English-Japanese translation
This addresses the issue of cultural insensitivity in LLM translations for users in multilingual workplace settings, but it is incremental as it builds on existing prompting methods.
The paper tackled the problem of whether LLMs support culturally appropriate communication by analyzing English-Japanese translations of workplace e-mails, finding that culturally-tailored prompting can improve cultural fit.
Large language models (LLMs) are increasingly used in everyday communication, including multilingual interactions across different cultural contexts. While LLMs can now generate near-perfect literal translations, it remains unclear whether LLMs support culturally appropriate communication. In this paper, we analyze the cultural sensitivity of different LLM designs when applied to English-Japanese translations of workplace e-mails. Here, we vary the prompting strategies: (1) naive "just translate" prompts, (2) audience-targeted prompts specifying the recipient's cultural background, and (3) instructional prompts with explicit guidance on Japanese communication norms. Using a mixed-methods study, we then analyze culture-specific language patterns to evaluate how well translations adapt to cultural norms. Further, we examine the appropriateness of the tone of the translations as perceived by native speakers. We find that culturally-tailored prompting can improve cultural fit, based on which we offer recommendations for designing culturally inclusive LLMs in multilingual settings.