List your company

Preference Alignment Data Selection on Aggregate Utility-Robustness Preference Pool (test)

97.68Robustness Score (R)Whole
60.104869.859979.61589.3701Jun 4, 2026

Evaluation results

MethodLinks
WholeBase Model=LLaMA3.2-3B, Selection Budget=10k, Tier=T32026.0697.6860.25
WholeBase Model=LLaMA3.2-3B, Selection Budget=30k, Tier=T32026.0697.6860.25
DOG-DBase Model=LLaMA3.2-3B, Selection Budget=30k, Tier=T22026.0696.5757.6
DOGBase Model=LLaMA3.2-3B, Selection Budget=30k, Tier=T22026.0696.0857.2
RM-RSBase Model=LLaMA3.2-3B, Selection Budget=30k, Tier=T22026.0696.0355.9
DOG-DBase Model=LLaMA3.2-3B, Selection Budget=10k, Tier=T22026.0695.6355.8
SDPOBase Model=LLaMA3.2-3B, Selection Budget=10k, Tier=T32026.0693.5855.65
SDPOBase Model=LLaMA3.2-3B, Selection Budget=30k, Tier=T32026.0691.6356.25
DOGBase Model=LLaMA3.2-3B, Selection Budget=10k, Tier=T22026.0690.8355.7
KMeansBase Model=LLaMA3.2-3B, Selection Budget=10k, Tier=T22026.0690.7155.15
KMeansBase Model=LLaMA3.2-3B, Selection Budget=30k, Tier=T22026.0689.8356.95
LaserBase Model=LLaMA3.2-3B, Selection Budget=10k, Tier=T22026.0689.6556.3
LaserBase Model=LLaMA3.2-3B, Selection Budget=30k, Tier=T22026.068656.3
RM-RSBase Model=LLaMA3.2-3B, Selection Budget=10k, Tier=T22026.0685.654.85
DEITABase Model=LLaMA3.2-3B, Selection Budget=30k, Tier=T22026.0682.8654.64
RandomBase Model=LLaMA3.2-3B, Selection Budget=30k, Tier=T12026.0681.1354.05
RandomBase Model=LLaMA3.2-3B, Selection Budget=10k, Tier=T12026.0680.9553.8
DEITABase Model=LLaMA3.2-3B, Selection Budget=10k, Tier=T22026.0680.2654.38
SDPOBase Model=Gemma3-1B, Selection Budget=30k, Tier=T32026.0678.8856.25
DOG-DBase Model=Gemma3-1B, Selection Budget=30k, Tier=T22026.0677.2547.1
DOGBase Model=Gemma3-1B, Selection Budget=30k, Tier=T22026.0676.946.2
DOG-DBase Model=Gemma3-1B, Selection Budget=10k, Tier=T22026.0676.545.8
LaserBase Model=Gemma3-1B, Selection Budget=30k, Tier=T22026.0676.545.55
KMeansBase Model=Gemma3-1B, Selection Budget=30k, Tier=T22026.0674.8548.65
BaseBase Model=LLaMA3.2-3B, Selection Budget=10k, Tier=T12026.0674.652.45
BaseBase Model=LLaMA3.2-3B, Selection Budget=30k, Tier=T12026.0674.652.45
SDPOBase Model=Gemma3-1B, Selection Budget=10k, Tier=T32026.0674.3855.65
WholeBase Model=Gemma3-1B, Selection Budget=10k, Tier=T32026.0674.3845.89
WholeBase Model=Gemma3-1B, Selection Budget=30k, Tier=T32026.0674.3845.89
LaserBase Model=Gemma3-1B, Selection Budget=10k, Tier=T22026.0673.246.05
DOGBase Model=Gemma3-1B, Selection Budget=10k, Tier=T22026.0672.743.8
RM-RSBase Model=Gemma3-1B, Selection Budget=30k, Tier=T22026.0671.6545.95
KMeansBase Model=Gemma3-1B, Selection Budget=10k, Tier=T22026.0671.344.85
RandomBase Model=Gemma3-1B, Selection Budget=30k, Tier=T12026.0669.243.5
RandomBase Model=Gemma3-1B, Selection Budget=10k, Tier=T12026.0667.8842.75
DEITABase Model=Gemma3-1B, Selection Budget=10k, Tier=T22026.0667.6541.44
DEITABase Model=Gemma3-1B, Selection Budget=30k, Tier=T22026.0667.6543.47
RM-RSBase Model=Gemma3-1B, Selection Budget=10k, Tier=T22026.0667.4543.55
BaseBase Model=Gemma3-1B, Selection Budget=10k, Tier=T12026.0661.5541.04
BaseBase Model=Gemma3-1B, Selection Budget=30k, Tier=T12026.0661.5541.04