| Mobile Web

KAIST develops AI system to diagnose time reasoning errors using database

KAIST said on Monday a research team led by professor Eui-jong Hwang developed a system that automatically evaluates and diagnoses large language models\' time reasoning, in joint research with Microsoft Research. The team introduced temporal database design theory to AI evaluation, enabling a database to automatically generate 13 types of complex time-based questions and automate the process from answer derivation to verification. It also introduced a metric to validate dates and periods, improving detection of temporal hallucinations by 21.7 percent on average.