引导式测验 · 中等 等级
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.
问题 1 的 8
引导式测验 · 中等 等级
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.