Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Counterfactual Fairness on RealToxicityPrompts RTP-C
Loading...
0.2
Sentiment Parity
Gem-Fl
0.108
0.729
1.35
1.971
Jul 15, 2024
Sentiment Parity
C-ROUGE-L
C-BLEU
C-Cosine Similarity
Updated 1mo ago
Evaluation Results
Method
Method
Links
Sentiment Parity
C-ROUGE-L
C-BLEU
C-Cosine Similarity
Gem-Fl
Model=Gem-Fl
2024.07
0.2
32.6
17
48.9
Gem-Fl-Lt
Model=Gem-Fl-Lt
2024.07
0.6
50.2
35.3
64.6
GPT-4o-m
Model=GPT-4o-m
2024.07
1.7
55.9
45.4
69.6
Gem-Pro
Model=Gem-Pro
2024.07
1.9
29.7
16.4
53.6
GPT-4o
Model=GPT-4o
2024.07
2.5
49.8
40.4
61.4
Feedback
Search any
task
Search any
task