List your company

Helpful Assistant Alignment on Helpful Assistant normalized rewards (test)

53Helpfulness Reward (r1)MOPO-Lag
19.7228.363745.64Dec 11, 2025

Evaluation results

MethodLinks
MOPO-LagModel=Zephyr-7b-beta2025.125351
MOPO-LagModel=Zephyr-7b-beta2025.125253
MOPO-LBModel=Zephyr-7b-beta2025.125152
MOPO-LBModel=Mistral-7b-vo.2 (Instruct)2025.124948
MOPO-LagModel=Mistral-7b-vo.2 (Instruct)2025.124947
MOPO-LBModel=Zephyr-7b-beta2025.124948
MOPO-LagModel=Llama-3.1-8B2025.124846
PARMModel=Mistral-7b-vo.2 (Instruct)2025.124847
PARMModel=Zephyr-7b-beta2025.124850
MOPO-LBModel=Llama-3.1-8B2025.124543
MOPO-LagModel=Mistral-7b-vo.2 (Instruct)2025.124547
PARMModel=Zephyr-7b-beta2025.124548
MOPO-LagModel=Llama-3.1-8B2025.124553
RiCModel=Zephyr-7b-beta2025.124547
RiCModel=Mistral-7b-vo.2 (Instruct)2025.124441
MOPO-LBModel=Mistral-7b-vo.2 (Instruct)2025.124445
MOPO-LagModel=OpenChat-v3.52025.124341
RiCModel=Zephyr-7b-beta2025.124346
RiCModel=Llama-3.1-8B2025.124341
RiCModel=Mistral-7b-vo.2 (Instruct)2025.124344
MOPO-LagModel=OpenChat-v3.52025.124240
MOPO-LBModel=Llama-3.1-8B2025.124250
MOPO-LBModel=OpenChat-v3.52025.124139
RiCModel=Llama-3.1-8B2025.124147
MODPOModel=Mistral-7b-vo.2 (Instruct)2025.124139
PARMModel=Mistral-7b-vo.2 (Instruct)2025.124146
RiCModel=OpenChat-v3.52025.124033
PARMModel=Llama-3.1-8B2025.124042
MOPO-LBModel=OpenChat-v3.52025.124039
MODPOModel=Mistral-7b-vo.2 (Instruct)2025.124042
MODPOModel=Zephyr-7b-beta2025.124040
MODPOModel=OpenChat-v3.52025.123937
PARMModel=OpenChat-v3.52025.123837
DPO on D_JModel=Zephyr-7b-beta2025.123841
MOPO-LagModel=phi-1.52025.123736
RiCModel=OpenChat-v3.52025.123740
MODPOModel=Llama-3.1-8B2025.123745
PARMModel=OpenChat-v3.52025.123639
DPO on D_JModel=OpenChat-v3.52025.123635
DPO on D_JModel=Mistral-7b-vo.2 (Instruct)2025.123639
MODPOModel=OpenChat-v3.52025.123533
MODPOModel=Zephyr-7b-beta2025.123533
PARMModel=Llama-3.1-8B2025.123544
DPO on D_JModel=Llama-3.1-8B2025.123540
DPO on D_JModel=Zephyr-7b-beta2025.123438
MOPO-LBModel=phi-1.52025.123435
PARMModel=phi-1.52025.123332
MODPOModel=Llama-3.1-8B2025.123233
DPO on D_JModel=Mistral-7b-vo.2 (Instruct)2025.123230
DPO on D_JModel=Llama-3.1-8B2025.123130
RiCModel=phi-1.52025.123127
MOPO-LagModel=phi-1.52025.122926
PARMModel=phi-1.52025.122824
DPO on D_JModel=OpenChat-v3.52025.122826
MOPO-LBModel=phi-1.52025.122724
DPO on D_JModel=phi-1.52025.122725
MODPOModel=phi-1.52025.122524
RiCModel=phi-1.52025.122321
DPO on D_JModel=phi-1.52025.122219
MODPOModel=phi-1.52025.122120