Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Detection of LLM-Generated Text on XSum GPT-J-6B
Loading...
88.35
AUROC
SurpMark ref-attack
69.0476
74.0588
79.07
84.0812
Oct 8, 2025
AUROC
Updated 21d ago
Evaluation Results
Method
Method
Links
AUROC
SurpMark ref-attack
Adversarial Attack Typ...
2025.10
88.35
SurpMark test-attack
Adversarial Attack Typ...
2025.10
88.35
SurpMark both-attack
Adversarial Attack Typ...
2025.10
88.35
SurpMark test-attack
Adversarial Attack Typ...
2025.10
86.37
Lastde++
Adversarial Attack Typ...
2025.10
85.38
SurpMark both-attack
Adversarial Attack Typ...
2025.10
85.23
SurpMark test-attack
Adversarial Attack Typ...
2025.10
84.86
SurpMark both-attack
Adversarial Attack Typ...
2025.10
84.44
SurpMark ref-attack
Adversarial Attack Typ...
2025.10
83.85
SurpMark ref-attack
Adversarial Attack Typ...
2025.10
83.84
Fast-DetectGPT
Adversarial Attack Typ...
2025.10
78.6
Fast-DetectGPT
Adversarial Attack Typ...
2025.10
75.44
Fast-DetectGPT
Adversarial Attack Typ...
2025.10
74.09
Lastde++
Adversarial Attack Typ...
2025.10
73.55
Lastde++
Adversarial Attack Typ...
2025.10
69.79
Feedback
Search any
task
Search any
task