Comparing generative artificial intelligence tools to voice assistants using reference interactions

This study investigates the ability of voice assistants and generative AI tools to respond to reference questions traditionally received by academic librarians. The authors created a sample of 25 questions based on queries received on the virtual reference service at their institution. They then created a rubric to evaluate the quality of the answers that the AI powered tools provided. The authors determined that the tools understand reference questions well and provide relevant answers but that the quality of the references provided, and the accuracy of the answers can be lacking. They suggest that more research needs to be done to understand the place of AI powered tools in reference services.