ConceptAI & ML
Test-time Contamination
The issue where models regurgitate information seen during training while being evaluated, leading to misleading benchmark results.
Know first
Named as a prerequisite by the lectures that define this. The number is how many say so. A grey one has no page yet.
Evaluation benchmarks1LLM training data1
Lecturers
1Connections
1The lectures that define it or assume it, and the concepts next to it.