Assessment Checklist
Assessment checklists are structured frameworks designed to systematically evaluate the performance and reliability of various systems, particularly in complex domains like AI and healthcare. Current research focuses on developing checklists tailored to specific applications, such as evaluating the safety of autonomous vehicles, the ethical implications of generative AI in medicine, and the robustness of large language models in mathematical reasoning. These checklists aim to improve transparency, reproducibility, and ultimately, the trustworthiness of research findings and deployed systems, leading to more reliable and responsible technological advancements.
Papers
August 14, 2024
August 7, 2024
August 6, 2024
July 23, 2024
July 19, 2024
July 11, 2024
March 27, 2024
March 5, 2024
November 2, 2023
August 14, 2023
July 5, 2023
June 16, 2023
November 17, 2022
November 14, 2022
September 12, 2022
July 6, 2022
July 1, 2022
June 4, 2022
May 24, 2022
January 27, 2022