List your company

Alignment on HH-RLHF

154Estimated Score (EST)AdaBoN
147.76149.38151152.62May 17, 2025

Evaluation results

MethodLinks
AdaBoNLM=Qwen, RM=Armo, K=5, B=120, d=0.75B2025.05154
AdaBoNLM=Llama, RM=Armo, K=5, B=120, d=0.75B2025.05154
AdaBoNLM=Llama, RM=Mistral, K=5, B=120, d=0.75B2025.05153
AdaBoNLM=Mistral, RM=Mistral, K=5, B=120, d=0.75B2025.05151
AdaBoNLM=Mistral, RM=FsfairX, K=5, B=120, d=0.75B2025.05151
AdaBoNLM=Mistral, RM=Armo, K=5, B=120, d=0.75B2025.05151
AdaBoNLM=Qwen, RM=FsfairX, K=5, B=120, d=0.75B2025.05150
AdaBoNLM=Gemma, RM=Armo, K=5, B=120, d=0.75B2025.05150
AdaBoNLM=Llama, RM=FsfairX, K=5, B=120, d=0.75B2025.05150
AdaBoNLM=Gemma, RM=Mistral, K=5, B=120, d=0.75B2025.05149
AdaBoNLM=Gemma, RM=FsfairX, K=5, B=120, d=0.75B2025.05149
AdaBoNLM=Qwen, RM=Mistral, K=5, B=120, d=0.75B2025.05148