From Information-Seeking to Information-Asking: Designing RefuGPT, a Chatbot for Ukrainian Refugees in Switzerland

A key challenge for refugees is accessing relevant information about their host country. However, refugees often face disorientation during their information-seeking process. Disorientation is driven by language barriers, a digital divide, high urgency, and an evolving situation, which hinders the refugees’ ability to access information. Addressing the issue of disorientation, we propose an IT artifact, i.e., a chatbot called RefuGPT , designed through a rigorous Design Science Research Methodology. RefuGPT leverages the power of a large language model (LLM), GPT-4 while accessing two distinct sources of information, i.e., official and community-based information utilizing retrieval augmented generation and prompt-based learning (Figure 1 ). We assess RefuGPT's usefulness and usability through an ex-post evaluation in a naturalistic setting with Ukrainian refugees. Hence, we show that our bi-layered LLM-based chatbot can effectively assist refugees. They thus move from information-seeking to a more effortless information-asking. Based on those insights, we propose design principles as well as practical recommendations for refugee chatbots.