Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
AI-generated text detection on Long-form QA 9K pooled generations corpus
Loading...
100
Detection Accuracy (at 1% FPR)
SP (Retrieval over 9K)
74.416
81.058
87.7
94.342
Mar 23, 2023
Detection Accuracy (at 1% FPR)
Updated 3d ago
Evaluation Results
Method
Method
Links
Detection Accuracy (at 1% FPR)
SP (Retrieval over 9K)
Generator Model=GPT2-X...
2023.03
100
SP (Retrieval over 9K)
Generator Model=OPT-13...
2023.03
100
SP (Retrieval over 9K)
Generator Model=GPT-3....
2023.03
100
BM25 (Retrieval over 9K)
Generator Model=GPT2-X...
2023.03
100
BM25 (Retrieval over 9K)
Generator Model=OPT-13...
2023.03
100
BM25 (Retrieval over 9K)
Generator Model=GPT-3....
2023.03
100
BM25 (Retrieval over 9K)
Generator Model=OPT-13...
2023.03
98.5
BM25 (Retrieval over 9K)
Generator Model=GPT-3....
2023.03
98.5
BM25 (Retrieval over 9K)
Generator Model=GPT2-X...
2023.03
98.3
BM25 (Retrieval over 9K)
Generator Model=GPT-3....
2023.03
96
BM25 (Retrieval over 9K)
Generator Model=GPT2-X...
2023.03
95.2
BM25 (Retrieval over 9K)
Generator Model=OPT-13...
2023.03
94.4
SP (Retrieval over 9K)
Generator Model=GPT-3....
2023.03
93.8
SP (Retrieval over 9K)
Generator Model=OPT-13...
2023.03
89.6
SP (Retrieval over 9K)
Generator Model=GPT2-X...
2023.03
88.9
SP (Retrieval over 9K)
Generator Model=GPT-3....
2023.03
84.6
SP (Retrieval over 9K)
Generator Model=OPT-13...
2023.03
76.4
SP (Retrieval over 9K)
Generator Model=GPT2-X...
2023.03
75.4
Feedback
Search any
task
Search any
task