List your company

Multi-objective personalized alignment on Multifaceted

51AMRMATO
2.1214.8127.540.19May 25, 2026

Evaluation results

MethodLinks
MATOBackbone=Qwen3-8B, Judge Model=claude-sonnet-4-52026.05513.72.61
OPADBackbone=Qwen3-8B, Judge Model=claude-sonnet-4-52026.05503.72.57
Preference PromptBackbone=Qwen3-8B, Judge Model=claude-sonnet-4-52026.05473.612.47
Linear AlignmentBackbone=Qwen3-8B, Judge Model=claude-sonnet-4-52026.05463.592.48
CoSBackbone=Qwen3-8B, Judge Model=claude-sonnet-4-52026.05433.452.36
Preference PromptBackbone=Llama-3.1-8B, Judge Model=claude-sonnet-4-52026.05423.392.32
MATOBackbone=Llama-3.1-8B, Judge Model=claude-sonnet-4-52026.05423.452.4
OPADBackbone=Llama-3.1-8B, Judge Model=claude-sonnet-4-52026.05393.42.33
AmuletBackbone=Qwen3-8B, Judge Model=claude-sonnet-4-52026.05353.242.23
Linear AlignmentBackbone=Llama-3.1-8B, Judge Model=claude-sonnet-4-52026.05353.292.22
CoSBackbone=Llama-3.1-8B, Judge Model=claude-sonnet-4-52026.05273.012.02
Base LLMBackbone=Qwen3-8B, Judge Model=claude-sonnet-4-52026.05253.091.89
Base LLMBackbone=Llama-3.1-8B, Judge Model=claude-sonnet-4-52026.05212.881.76
MATOBackbone=Llama-3.2-1B, Judge Model=claude-sonnet-4-52026.05162.641.72
AmuletBackbone=Llama-3.1-8B, Judge Model=claude-sonnet-4-52026.05162.591.74
OPADBackbone=Llama-3.2-1B, Judge Model=claude-sonnet-4-52026.05152.591.67
Preference PromptBackbone=Llama-3.2-1B, Judge Model=claude-sonnet-4-52026.05132.621.62
Linear AlignmentBackbone=Llama-3.2-1B, Judge Model=claude-sonnet-4-52026.05122.481.62
MATOBackbone=Qwen3-0.6B, Judge Model=claude-sonnet-4-52026.05102.551.55
Base LLMBackbone=Llama-3.2-1B, Judge Model=claude-sonnet-4-52026.0592.41.5
Preference PromptBackbone=Qwen3-0.6B, Judge Model=claude-sonnet-4-52026.0582.411.43
Linear AlignmentBackbone=Qwen3-0.6B, Judge Model=claude-sonnet-4-52026.0582.391.49
OPADBackbone=Qwen3-0.6B, Judge Model=claude-sonnet-4-52026.0582.521.5
CoSBackbone=Qwen3-0.6B, Judge Model=claude-sonnet-4-52026.0562.31.44
CoSBackbone=Llama-3.2-1B, Judge Model=claude-sonnet-4-52026.0562.051.38
Base LLMBackbone=Qwen3-0.6B, Judge Model=claude-sonnet-4-52026.0552.251.33
AmuletBackbone=Qwen3-0.6B, Judge Model=claude-sonnet-4-52026.0542.091.35
AmuletBackbone=Llama-3.2-1B, Judge Model=claude-sonnet-4-52026.0541.841.27