@prefix schema: <https://schema.org/> .
@prefix af: <https://anchorfact.org/ns#> .

<https://anchorfact.org/kb/ai/evaluation-datasets-and-golden-tests-for-llms>
  a schema:TechArticle ;
  schema:headline "Evaluation Datasets and Golden Tests for LLMs" ;
  schema:url <https://anchorfact.org/ai/evaluation-datasets-and-golden-tests-for-llms/> ;
  af:status "public" ;
  af:confidence "medium" ;
  af:confidenceScore "0.725" ;
  af:confidenceBasis "verified_sources" ;
  af:generationMethod "ai_structured" .

<https://anchorfact.org/kb/ai/evaluation-datasets-and-golden-tests-for-llms>
  schema:citation <https://github.com/openai/evals> ;
  af:sourceTier "B" .

<https://anchorfact.org/kb/ai/evaluation-datasets-and-golden-tests-for-llms>
  schema:citation <https://crfm.stanford.edu/helm/latest/> ;
  af:sourceTier "C" .

<https://anchorfact.org/kb/ai/evaluation-datasets-and-golden-tests-for-llms>
  schema:citation <https://github.com/google/BIG-bench> ;
  af:sourceTier "C" .