Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Factuality Evaluation on AggreFact-CNN (FTS)
Loading...
70.3
Balanced Accuracy
SummaC-Cv
47.108
53.129
59.15
65.171
Mar 4, 2024
Balanced Accuracy
Updated 4d ago
Evaluation Results
Method
Method
Links
Balanced Accuracy
SummaC-Cv
variant=Convolutional
2024.03
70.3
FENICEGPT_claims
Extractor=LLM-based cl...
2024.03
68.2
ChatGPT-ZS
Prompting=Zero-shot
2024.03
66.2
TrueTeacher-11B
Parameters=11B
2024.03
65.7
QuestEval
2024.03
63.7
SummaC-ZS
variant=Zero-shot
2024.03
63.3
QAFactEval
2024.03
61.6
FENICET5_claims
Extractor=Knowledge-di...
2024.03
61.6
DAE
Note=Trained on XSumFaith
2024.03
59.4
ChatGPT-Star
Prompting=Scale-based
2024.03
55.8
AlignScore
2024.03
53.5
MENLI
2024.03
51.7
Random Baseline
2024.03
50
ChatGPT-CoT
Prompting=Chain-of-Tho...
2024.03
49.7
ChatGPT-DA
Prompting=Direct Asses...
2024.03
48
Feedback
Search any
task
Search any
task