List your company

Long-form generation on Long-form generation datasets LOO - near OOD

0.3PRRHUQ-SATRMD
-0.1472-0.03110.0850.2011Apr 13, 2026

Evaluation results

MethodLinks
HUQ-SATRMDModel Backbone=Llama 3.1-8B2026.040.3
HUQ-SATMDModel Backbone=Gemma-2-9B2026.040.2
SATMDModel Backbone=Gemma-2-9B2026.040.12
SATMD-MSPModel Backbone=Llama 3.1-8B2026.040.06
SAPLMA (top)Model Backbone=Llama 3.1-8B2026.040.04
HUQ-SATRMDModel Backbone=Gemma-2-9B2026.040.03
SATRMD-MSPModel Backbone=Llama 3.1-8B2026.040
SAPLMA (middle)Model Backbone=Gemma-2-9B2026.040
SAPLMA (middle)Model Backbone=Llama 3.1-8B2026.04-0.01
Lookback-lensModel Backbone=Llama 3.1-8B2026.04-0.01
HUQ-SATMDModel Backbone=Llama 3.1-8B2026.04-0.01
MSPModel Backbone=Llama 3.1-8B2026.04-0.01
SATRMDModel Backbone=Gemma-2-9B2026.04-0.01
Uhead (2 layers)Model Backbone=Llama 3.1-8B2026.04-0.02
SATRMDModel Backbone=Llama 3.1-8B2026.04-0.04
Uhead (1 layer)Model Backbone=Llama 3.1-8B2026.04-0.05
Uhead (1 layer)Model Backbone=Gemma-2-9B2026.04-0.05
SATMD-MSPModel Backbone=Gemma-2-9B2026.04-0.05
SAPLMA (top)Model Backbone=Gemma-2-9B2026.04-0.06
Lookback-lensModel Backbone=Gemma-2-9B2026.04-0.06
SATMDModel Backbone=Llama 3.1-8B2026.04-0.09
Uhead (2 layers)Model Backbone=Gemma-2-9B2026.04-0.09
MSPModel Backbone=Gemma-2-9B2026.04-0.1
SATRMD-MSPModel Backbone=Gemma-2-9B2026.04-0.13