For each input, we save the system’s first complete response (i.e., single-turn). Responses were scraped between late February and late March, 2023. Each query was issued in a separate browser session to avoid any history-based personalization.
Liu, N. F., Zhang, T., & Liang, P. (2023). Evaluating verifiability in generative search engines. https://doi.org/10.48550/arXiv.2304.09848 [liu2023evaluating]