Classification on AQUA
2.96ECECaliDist (As.)
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| CaliDist (As.)LLM=Gemma-3 (4B)2026.06 | 2.96 | 12.26 | |
| CaliDist (Sa.)LLM=Gemma-3 (4B)2026.06 | 4.49 | 10.83 | |
| CaliDist (Pr.)LLM=Gemma-3 (4B)2026.06 | 5.91 | 13.08 | |
| ConsistencyLLM=Phi-4-mini (3.8B)2026.06 | 5.93 | 13.6 | |
| CaliDist (As.)LLM=Phi-4-mini (3.8B)2026.06 | 5.97 | 15.11 | |
| CaliDist (Sa.)LLM=Phi-4-mini (3.8B)2026.06 | 6.15 | 13.99 | |
| CaliDist (Pr.)LLM=Phi-4-mini (3.8B)2026.06 | 9.64 | 14.99 | |
| Temperature ScalingLLM=Gemma-3 (4B)2026.06 | 10.07 | 15.77 | |
| Temperature ScalingLLM=Phi-4-mini (3.8B)2026.06 | 12.25 | 17.54 | |
| ConsistencyLLM=Gemma-3 (4B)2026.06 | 13.8 | 18.25 | |
| FSDLLM=Phi-4-mini (3.8B)2026.06 | 14.19 | 17.51 | |
| FSDLLM=Gemma-3 (4B)2026.06 | 15.85 | 19.04 | |
| VanillaLLM=Phi-4-mini (3.8B)2026.06 | 18.93 | 18.58 | |
| VanillaLLM=Gemma-3 (4B)2026.06 | 19.69 | 19.55 | |
| EntropyLLM=Gemma-3 (4B)2026.06 | 23.46 | 23.11 | |
| EntropyLLM=Phi-4-mini (3.8B)2026.06 | 26.33 | 23.27 |