Тест, свързан с ръководство · Среден Ниво

Building an LLM Eval Dataset Quiz

Tests sourcing real cases, golden answers versus rubrics, edge-case coverage, and sizing an eval set so score differences are meaningful.

Свързани ръководни пътекиBuilding LLM Eval Datasets
Въпрос 1 на 8

What does the guide recommend as the best starting source for eval cases?