Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Factuality Evaluation on AggreFact CNN (EXF)
Loading...
76.5
Balanced Accuracy
SummaC-ZS
48.94
56.095
63.25
70.405
Mar 4, 2024
Balanced Accuracy
Updated 4d ago
Evaluation Results
Method
Method
Links
Balanced Accuracy
SummaC-ZS
variant=Zero-shot
2024.03
76.5
AlignScore
2024.03
73.9
SummaC-Cv
variant=Convolutional
2024.03
69.8
QAFactEval
2024.03
69.1
FENICEGPT_claims
Extractor=LLM-based cl...
2024.03
68.8
DAE
Note=Trained on XSumFaith
2024.03
67.9
FENICET5_claims
Extractor=Knowledge-di...
2024.03
67.8
ChatGPT-Star
Prompting=Scale-based
2024.03
65.8
ChatGPT-ZS
Prompting=Zero-shot
2024.03
64.5
QuestEval
2024.03
64.3
ChatGPT-DA
Prompting=Direct Asses...
2024.03
63.6
ChatGPT-CoT
Prompting=Chain-of-Tho...
2024.03
60.4
TrueTeacher-11B
Parameters=11B
2024.03
57.7
MENLI
2024.03
52.8
Random Baseline
2024.03
50
Feedback
Search any
task
Search any
task