Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

LLaMA-2 generated sequences

Benchmarks

Task NameDataset NameSOTA ResultTrend
Watermark Robustness under GPT rephrasing attackLLaMA-2 generated sequences (1,000)
TPR@FPR=5%62.5
7
Showing 1 of 1 rows