List your company

Best-of-N Alignment on HH-RLHF (test)

98Percent batches with BWR > 0.50AdaBoN
52.2464.127687.88May 17, 2025

Evaluation results

MethodLinks
AdaBoNLM=Llama, RM=Mistral, K=5, B=120, d=0.75B2025.0598
AdaBoNLM=Mistral, RM=Mistral, K=5, B=120, d=0.75B2025.0594
AdaBoNLM=Mistral, RM=FsfairX, K=5, B=120, d=0.75B2025.0594
AdaBoNLM=Mistral, RM=Armo, K=5, B=120, d=0.75B2025.0592
AdaBoNLM=Llama, RM=Armo, K=5, B=120, d=0.75B2025.0592
AdaBoNLM=Llama, RM=FsfairX, K=5, B=120, d=0.75B2025.0582
AdaBoNLM=Qwen, RM=Mistral, K=5, B=120, d=0.75B2025.0580
AdaBoNLM=Qwen, RM=FsfairX, K=5, B=120, d=0.75B2025.0576
AdaBoNLM=Gemma, RM=Armo, K=5, B=120, d=0.75B2025.0576
AdaBoNLM=Qwen, RM=Armo, K=5, B=120, d=0.75B2025.0572
AdaBoNLM=Gemma, RM=Mistral, K=5, B=120, d=0.75B2025.0570
AdaBoNLM=Gemma, RM=FsfairX, K=5, B=120, d=0.75B2025.0554