List your company

Open Ended Generation on CNN DailyMail

24.3ROUGE-LConfAdapt
14.52417.06219.622.138Feb 5, 2026

Evaluation results

MethodLinks
ConfAdaptModel=L3.1-8B-Magpie, Chat Template=On, tau (τ)=0.9952026.0224.31.5
ConfAdaptModel=L3.1-8B-Magpie, Chat Template=On, tau (τ)=0.992026.0224.31.6
ConfAdaptModel=L3.1-8B-Magpie, Chat Template=On, tau (τ)=0.982026.0224.21.7
ConfAdaptModel=L3.1-8B-Magpie, Chat Template=On, tau (τ)=0.972026.0224.21.8
ConfAdaptModel=L3.1-8B-Magpie, Chat Template=On, tau (τ)=0.962026.0224.21.8
ConfAdaptModel=L3.1-8B-Magpie, Chat Template=On, tau (τ)=0.952026.0224.21.9
ConfAdaptModel=L3.1-8B-Magpie, Chat Template=On, tau (τ)=0.92026.0224.12.1
ConfAdaptModel=L3.1-8B-Magpie, Chat Template=On, tau (τ)=0.872026.0224.12.2
ConfAdaptModel=L3.1-8B-Magpie, Chat Template=On, tau (τ)=0.852026.02242.2
ConfAdaptModel=L3.1-8B-Magpie, Chat Template=On, tau (τ)=0.82026.0223.92.4
ConfAdaptModel=L3.1-8B-Magpie, Chat Template=On, tau (τ)=0.752026.0223.72.5
StaticModel=L3.1-8B-Magpie, Chat Template=On, k=12026.0223.61
ConfAdaptModel=L3.1-8B-Magpie, Chat Template=On, tau (τ)=0.72026.0223.62.7
ConfAdaptModel=Qwen3-4B-Inst-2507, Chat Template=Off, tau (τ)=0.9952026.0223.51.2
ConfAdaptModel=Qwen3-4B-Inst-2507, Chat Template=Off, tau (τ)=0.992026.0223.51.2
ConfAdaptModel=Qwen3-4B-Inst-2507, Chat Template=Off, tau (τ)=0.982026.0223.41.2
ConfAdaptModel=Qwen3-4B-Inst-2507, Chat Template=Off, tau (τ)=0.972026.0223.41.3
ConfAdaptModel=Qwen3-4B-Inst-2507, Chat Template=Off, tau (τ)=0.962026.0223.41.3
ConfAdaptModel=Qwen3-4B-Inst-2507, Chat Template=Off, tau (τ)=0.952026.0223.41.3
ConfAdaptModel=Qwen3-4B-Inst-2507, Chat Template=Off, tau (τ)=0.92026.0223.31.4
ConfAdaptModel=L3.1-8B-Magpie, Chat Template=On, tau (τ)=0.652026.0223.22.9
ConfAdaptModel=Qwen3-4B-Inst-2507, Chat Template=Off, tau (τ)=0.872026.0223.21.4
ConfAdaptModel=Qwen3-4B-Inst-2507, Chat Template=Off, tau (τ)=0.852026.0223.21.5
ConfAdaptModel=Qwen3-4B-Inst-2507, Chat Template=Off, tau (τ)=0.82026.0223.11.5
ConfAdaptModel=Qwen3-4B-Inst-2507, Chat Template=Off, tau (τ)=0.752026.02231.6
ConfAdaptModel=L3.1-8B-Magpie, Chat Template=On, tau (τ)=0.62026.0222.93.1
ConfAdaptModel=Qwen3-4B-Inst-2507, Chat Template=Off, tau (τ)=0.72026.0222.91.7
ConfAdaptModel=Qwen3-4B-Inst-2507, Chat Template=Off, tau (τ)=0.652026.0222.81.8
StaticModel=Qwen3-4B-Inst-2507, Chat Template=Off, k=12026.0222.71
ConfAdaptModel=Qwen3-4B-Inst-2507, Chat Template=Off, tau (τ)=0.62026.0222.71.9
Baseline Step 0Model=L3.1-8B-Magpie, Chat Template=On, k=12026.0222.61
StaticModel=L3.1-8B-Magpie, Chat Template=On, k=22026.0222.62
Baseline Step 0Model=Qwen3-4B-Inst-2507, Chat Template=Off, k=12026.0222.31
StaticModel=Qwen3-4B-Inst-2507, Chat Template=Off, k=22026.0222.22
StaticModel=L3.1-8B-Magpie, Chat Template=On, k=32026.0220.63
StaticModel=Qwen3-4B-Inst-2507, Chat Template=Off, k=32026.0220.53
StaticModel=Qwen3-4B-Inst-2507, Chat Template=Off, k=42026.0217.74
StaticModel=L3.1-8B-Magpie, Chat Template=On, k=42026.0217.64
StaticModel=Qwen3-4B-Inst-2507, Chat Template=Off, k=52026.0215.65
StaticModel=L3.1-8B-Magpie, Chat Template=On, k=52026.0214.95