1 event found.
PYData Seminar: Stop Early, Decide Smarter: Bayesian Sequential Testing for LLM Benchmarking
NDSM-Plein 85 1033 WC Amsterdam NDSM-Plein 85 1033 WC AmsterdamRyan Marinelli will be holding a tutorial at PyData, Amsterdam. Evaluating large language models is expensive. Standard benchmarking practices run fixed numbers of trials regardless of how quickly signal emerges, […]