Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Text Generation on Wikitext (Human Evaluation)
Loading...
88.7
Coherence: CD Better Rate
Contrastive Decoding
54.276
63.213
72.15
81.087
Oct 27, 2022
Coherence: CD Better Rate
Coherence: Same Rate
Coherence: Baseline Better Rate
Fluency: CD Better Rate
Fluency: Same Rate
Fluency: Baseline Better Rate
Updated 4d ago
Evaluation Results
Method
Method
Links
Coherence: CD Better Rate
Coherence: Same Rate
Coherence: Baseline Better Rate
Fluency: CD Better Rate
Fluency: Same Rate
Fluency: Baseline Better Rate
Contrastive Decoding
CD Model=GPT-2 XL, Bas...
2022.10
88.7
4.6
6.7
70.3
8.2
21.5
Contrastive Decoding
CD Model=OPT-13B, Base...
2022.10
77.3
10.6
12.1
68.7
15.2
16.2
Contrastive Decoding
CD Model=GPT-2 XL, Bas...
2022.10
71.4
8.3
20.2
54.8
8.3
36.9
Contrastive Decoding
CD Model=OPT-13B, Base...
2022.10
55.6
20.2
24.2
41.9
19.7
38.4
Feedback
Search any
task
Search any
task