SyncAI.news, a Varaisys broadcasting
Beyond Bilingual: Studying Quadrilingual Code-Switching with Conversational AI
AB

Annika Bush, Melika Minnaar, Salys Sultan, Tasnimul Hasan Tashin, Ankur Bhatt, Meltem Aksoy

· 1 min read

ResearcharXiv cs.CL

Beyond Bilingual: Studying Quadrilingual Code-Switching with Conversational AI

arXiv:2611.21394v1 Announce Type: cross Abstract: Multilingual speakers choose languages by topic and conversation partner. Large language models (LLMs) support these languages unequally. Research on code-switching with conversational AI has mostly examined bilingual pairs of well-resourced languages. In Cura\c{c}ao and Aruba, many people use Dutch, English, Spanish, and the low-resource Creole Papiamentu/o. In a preregistered study, 42 university students held two five-minute chatbot conversations, one about university life and one about local food and culture. Surveys assessed language background, AI use, and switching comfort. 20 international students in Cura\c{c}ao formed a comparison sample. Participants switched between turns and rarely mixed languages within a message. English dominated both conversations. Participants switched more often in the cultural conversation, where Papiamentu/o and Spanish rose from 15% to 24% of messages. Self-reports showed no lower comfort switching with the chatbot than with a person. Conversational agents must follow turn-by-turn language changes and handle local low-resource languages well.

Original source

This story was published by arXiv cs.CL and written by Annika Bush, Melika Minnaar, Salys Sultan, Tasnimul Hasan Tashin, Ankur Bhatt, Meltem Aksoy. SyncAI.news shows a preview; the complete article is on the publisher's site.

Read the full story on arxiv.org

Similar News