Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Dialogue Generation on Movie Dic (test)
Loading...
17.35
ROUGE-L
SECOND THOUGHTS (AEM + VM default)
9.9764
11.8907
13.805
15.7193
Jan 1, 2023
ROUGE-L
Perplexity
Updated 1mo ago
Evaluation Results
Method
Method
Links
ROUGE-L
Perplexity
SECOND THOUGHTS (AEM + VM default)
variant=AEM + VM (defa...
2023.01
17.35
9.23
SECOND THOUGHTS (AEM + AIL)
variant=AEM + AIL
2023.01
15.02
11.96
SECOND THOUGHTS (AEM Only)
variant=AEM Only
2023.01
14
10.55
InstructGPT
Service=Huge LM API se...
2023.01
11.47
11.58
GPT-3
Service=Huge LM API se...
2023.01
10.26
10.44
Feedback
Search any
task
Search any
task