Open Ended Generation on CNN DailyMail
24.3ROUGE-LConfAdapt
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| ConfAdaptModel=L3.1-8B-Magpie, Chat Template=On, tau (τ)=0.9952026.02 | 24.3 | 1.5 | |
| ConfAdaptModel=L3.1-8B-Magpie, Chat Template=On, tau (τ)=0.992026.02 | 24.3 | 1.6 | |
| ConfAdaptModel=L3.1-8B-Magpie, Chat Template=On, tau (τ)=0.982026.02 | 24.2 | 1.7 | |
| ConfAdaptModel=L3.1-8B-Magpie, Chat Template=On, tau (τ)=0.972026.02 | 24.2 | 1.8 | |
| ConfAdaptModel=L3.1-8B-Magpie, Chat Template=On, tau (τ)=0.962026.02 | 24.2 | 1.8 | |
| ConfAdaptModel=L3.1-8B-Magpie, Chat Template=On, tau (τ)=0.952026.02 | 24.2 | 1.9 | |
| ConfAdaptModel=L3.1-8B-Magpie, Chat Template=On, tau (τ)=0.92026.02 | 24.1 | 2.1 | |
| ConfAdaptModel=L3.1-8B-Magpie, Chat Template=On, tau (τ)=0.872026.02 | 24.1 | 2.2 | |
| ConfAdaptModel=L3.1-8B-Magpie, Chat Template=On, tau (τ)=0.852026.02 | 24 | 2.2 | |
| ConfAdaptModel=L3.1-8B-Magpie, Chat Template=On, tau (τ)=0.82026.02 | 23.9 | 2.4 | |
| ConfAdaptModel=L3.1-8B-Magpie, Chat Template=On, tau (τ)=0.752026.02 | 23.7 | 2.5 | |
| StaticModel=L3.1-8B-Magpie, Chat Template=On, k=12026.02 | 23.6 | 1 | |
| ConfAdaptModel=L3.1-8B-Magpie, Chat Template=On, tau (τ)=0.72026.02 | 23.6 | 2.7 | |
| ConfAdaptModel=Qwen3-4B-Inst-2507, Chat Template=Off, tau (τ)=0.9952026.02 | 23.5 | 1.2 | |
| ConfAdaptModel=Qwen3-4B-Inst-2507, Chat Template=Off, tau (τ)=0.992026.02 | 23.5 | 1.2 | |
| ConfAdaptModel=Qwen3-4B-Inst-2507, Chat Template=Off, tau (τ)=0.982026.02 | 23.4 | 1.2 | |
| ConfAdaptModel=Qwen3-4B-Inst-2507, Chat Template=Off, tau (τ)=0.972026.02 | 23.4 | 1.3 | |
| ConfAdaptModel=Qwen3-4B-Inst-2507, Chat Template=Off, tau (τ)=0.962026.02 | 23.4 | 1.3 | |
| ConfAdaptModel=Qwen3-4B-Inst-2507, Chat Template=Off, tau (τ)=0.952026.02 | 23.4 | 1.3 | |
| ConfAdaptModel=Qwen3-4B-Inst-2507, Chat Template=Off, tau (τ)=0.92026.02 | 23.3 | 1.4 | |
| ConfAdaptModel=L3.1-8B-Magpie, Chat Template=On, tau (τ)=0.652026.02 | 23.2 | 2.9 | |
| ConfAdaptModel=Qwen3-4B-Inst-2507, Chat Template=Off, tau (τ)=0.872026.02 | 23.2 | 1.4 | |
| ConfAdaptModel=Qwen3-4B-Inst-2507, Chat Template=Off, tau (τ)=0.852026.02 | 23.2 | 1.5 | |
| ConfAdaptModel=Qwen3-4B-Inst-2507, Chat Template=Off, tau (τ)=0.82026.02 | 23.1 | 1.5 | |
| ConfAdaptModel=Qwen3-4B-Inst-2507, Chat Template=Off, tau (τ)=0.752026.02 | 23 | 1.6 | |
| ConfAdaptModel=L3.1-8B-Magpie, Chat Template=On, tau (τ)=0.62026.02 | 22.9 | 3.1 | |
| ConfAdaptModel=Qwen3-4B-Inst-2507, Chat Template=Off, tau (τ)=0.72026.02 | 22.9 | 1.7 | |
| ConfAdaptModel=Qwen3-4B-Inst-2507, Chat Template=Off, tau (τ)=0.652026.02 | 22.8 | 1.8 | |
| StaticModel=Qwen3-4B-Inst-2507, Chat Template=Off, k=12026.02 | 22.7 | 1 | |
| ConfAdaptModel=Qwen3-4B-Inst-2507, Chat Template=Off, tau (τ)=0.62026.02 | 22.7 | 1.9 | |
| Baseline Step 0Model=L3.1-8B-Magpie, Chat Template=On, k=12026.02 | 22.6 | 1 | |
| StaticModel=L3.1-8B-Magpie, Chat Template=On, k=22026.02 | 22.6 | 2 | |
| Baseline Step 0Model=Qwen3-4B-Inst-2507, Chat Template=Off, k=12026.02 | 22.3 | 1 | |
| StaticModel=Qwen3-4B-Inst-2507, Chat Template=Off, k=22026.02 | 22.2 | 2 | |
| StaticModel=L3.1-8B-Magpie, Chat Template=On, k=32026.02 | 20.6 | 3 | |
| StaticModel=Qwen3-4B-Inst-2507, Chat Template=Off, k=32026.02 | 20.5 | 3 | |
| StaticModel=Qwen3-4B-Inst-2507, Chat Template=Off, k=42026.02 | 17.7 | 4 | |
| StaticModel=L3.1-8B-Magpie, Chat Template=On, k=42026.02 | 17.6 | 4 | |
| StaticModel=Qwen3-4B-Inst-2507, Chat Template=Off, k=52026.02 | 15.6 | 5 | |
| StaticModel=L3.1-8B-Magpie, Chat Template=On, k=52026.02 | 14.9 | 5 |