Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Question Generation on FairytaleQA (Human Preference Evaluation)
Loading...
53
Grammaticality Wins
SkillQG
46.032
47.841
49.65
51.459
May 8, 2023
Grammaticality Wins
Grammaticality Ties
Answerability Wins
Answerability Ties
Relevance Wins
Relevance Ties
Updated 1mo ago
Evaluation Results
Method
Method
Links
Grammaticality Wins
Grammaticality Ties
Answerability Wins
Answerability Ties
Relevance Wins
Relevance Ties
SkillQG
baseline_comparison=NQG++
2023.05
53
10
53.6
5.6
54
3.7
CQG
baseline_comparison=NQG++
2023.05
50.3
4
51.3
5
52
7
CSQG
baseline_comparison=NQG++
2023.05
49
7.3
49.2
5.3
49.4
6
QTD
baseline_comparison=NQG++
2023.05
48.7
9.3
48.3
2.7
48.2
6.3
QAG
baseline_comparison=NQG++
2023.05
46.3
8.7
47
9
41.7
20.5
Feedback
Search any
task
Search any
task