ResearchTasksWatermark Robustness under GPT rephrasing attackWatermark Robustness under GPT rephrasing attackFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedLLaMA-2 generated sequences (1,000)MCmark62.5TPR@FPR=5%7Feb 26, 2026