Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Hallucination Annotation on ANAH v1 (test)
Loading...
89.3
F1 Score
ANAH-v2
78.2656
81.1303
83.995
86.8597
Jul 5, 2024
F1 Score
Accuracy
RougeL
BERTScore
Updated 4d ago
Evaluation Results
Method
Method
Links
F1 Score
Accuracy
RougeL
BERTScore
ANAH-v2
Stage=Stage 3, Backbon...
2024.07
89.3
89.55
69.44
91.43
ANAH-v2
Stage=Stage 2, Backbon...
2024.07
87.75
88.18
67.28
90.8
GPT-4
2024.07
87.11
86.97
86.32
96.21
ANAH-v2
Stage=Stage 1, Backbon...
2024.07
84.45
84.85
60.1
88.43
ANAH-20B
Parameters=20B
2024.07
80.49
81.01
58.82
88.44
ANAH-7B
Parameters=7B
2024.07
78.69
79.92
58.51
87.27
Feedback
Search any
task
Search any
task