Book
Open access
Jul 2026
LLMs or Naive Bayes? Old Gems or New Ways
It is shown the decision line is task-dependent (NB reaches LLM parity around N ∼ 104 labels for topic classification, while zero-data sentiment favors the LLM at all N tested) and a Kubernetes Helm operator is provided that automates model selection using configurable thresholds and verifiable Prometheus metrics.
M. Sada, John J. Graham, M. Tatineni et al.
· Practice and Experience in A... · 0 citations