Question Answering on ARC-c (Accuracy, Exit Position)
51.5AccuracyBackbone
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| BackboneBackbone Model=Llama3.1 8B (32 layers)2026.04 | 51.5 | — | |
| River-LLMBackbone Model=Llama3.1 8B (32 layers), Threshold (τ)=0.72026.04 | 51.2 | 8.44 | |
| River-LLMBackbone Model=Llama3.1 8B (32 layers), Threshold (τ)=0.52026.04 | 50.3 | 3.01 | |
| River-LLMBackbone Model=Llama3.2 1B (16 layers), Threshold (τ)=0.72026.04 | 35.9 | 10.68 | |
| BackboneBackbone Model=Llama3.2 1B (16 layers)2026.04 | 35.7 | — | |
| River-LLMBackbone Model=Llama3.2 1B (16 layers), Threshold (τ)=0.52026.04 | 35.2 | 3.24 |