Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Factuality Evaluation on AggreFact-CNN (OLD)
Loading...
82.1
Balanced Accuracy
FENICEGPT_claims
48.716
57.383
66.05
74.717
Mar 4, 2024
Balanced Accuracy
Updated 4d ago
Evaluation Results
Method
Method
Links
Balanced Accuracy
FENICEGPT_claims
Extractor=LLM-based cl...
2024.03
82.1
TrueTeacher-11B
Parameters=11B
2024.03
81.9
FENICET5_claims
Extractor=Knowledge-di...
2024.03
80.6
QAFactEval
2024.03
80.3
SummaC-Cv
variant=Convolutional
2024.03
78.9
AlignScore
2024.03
78
SummaC-ZS
variant=Zero-shot
2024.03
76.3
ChatGPT-ZS
Prompting=Zero-shot
2024.03
74.3
ChatGPT-Star
Prompting=Scale-based
2024.03
71.2
ChatGPT-DA
Prompting=Direct Asses...
2024.03
71
DAE
Note=Trained on XSumFaith
2024.03
69.7
MENLI
2024.03
68.4
ChatGPT-CoT
Prompting=Chain-of-Tho...
2024.03
66.7
QuestEval
2024.03
65.2
Random Baseline
2024.03
50
Feedback
Search any
task
Search any
task