Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Factuality Evaluation on AggreFact-XSum FTS
Loading...
80.2
Balanced Accuracy
AlignScore
48.792
56.946
65.1
73.254
Mar 4, 2024
Balanced Accuracy
Updated 4d ago
Evaluation Results
Method
Method
Links
Balanced Accuracy
AlignScore
2024.03
80.2
TrueTeacher-11B
Parameters=11B
2024.03
75.2
FENICEGPT_claims
Extractor=LLM-based cl...
2024.03
73.9
DAE
Note=Trained on XSumFaith
2024.03
73.1
FENICET5_claims
Extractor=Knowledge-di...
2024.03
71.4
SummaC-Cv
variant=Convolutional
2024.03
67
QAFactEval
2024.03
65.9
ChatGPT-ZS
Prompting=Zero-shot
2024.03
62.6
QuestEval
2024.03
61.6
MENLI
2024.03
58.3
ChatGPT-Star
Prompting=Scale-based
2024.03
57.7
SummaC-ZS
variant=Zero-shot
2024.03
56.1
ChatGPT-CoT
Prompting=Chain-of-Tho...
2024.03
56
ChatGPT-DA
Prompting=Direct Asses...
2024.03
53.6
Random Baseline
2024.03
50
Feedback
Search any
task
Search any
task