quiz bu lëkkale ak tegtal · Diggante Niveau
Benchmark Contamination Quiz
Tests how benchmark items leak into training data, detection methods like n-gram overlap and Min-K% Prob, and mitigations such as canaries and time splits.
Laaj 1 de 8
quiz bu lëkkale ak tegtal · Diggante Niveau
Tests how benchmark items leak into training data, detection methods like n-gram overlap and Min-K% Prob, and mitigations such as canaries and time splits.