Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Best-of-N Alignment on HH-RLHF
Loading...
53
BWR
AdaBoN
52.72
54.61
56.5
58.39
May 17, 2025
BWR
Updated 1mo ago
Evaluation Results
Method
Method
Links
BWR
AdaBoN
LM=Qwen, RM=Armo, batc...
2025.05
53
AdaBoN
LM=Gemma, RM=FsfairX,...
2025.05
53
AdaBoN
LM=Qwen, RM=FsfairX, b...
2025.05
54
AdaBoN
LM=Gemma, RM=Mistral,...
2025.05
54
AdaBoN
LM=Mistral, RM=Armo, b...
2025.05
55
AdaBoN
LM=Qwen, RM=Mistral, b...
2025.05
55
AdaBoN
LM=Gemma, RM=Armo, bat...
2025.05
55
AdaBoN
LM=Llama, RM=FsfairX,...
2025.05
57
AdaBoN
LM=Llama, RM=Armo, bat...
2025.05
57
AdaBoN
LM=Mistral, RM=Mistral...
2025.05
58
AdaBoN
LM=Llama, RM=Mistral,...
2025.05
59
AdaBoN
LM=Mistral, RM=FsfairX...
2025.05
60
Feedback
Search any
task
Search any
task