引導式測驗 · 中等 等級
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.
問題 1 的 8
引導式測驗 · 中等 等級
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.