Uncertainty Quantification on LongFact
-0.017PCCEcc
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| EccModel=Llama3-70B2026.04 | -0.017 | -0.036 | |
| DegModel=Llama3-70B2026.04 | -0.025 | -0.053 | |
| SEModel=Llama3-70B2026.04 | -0.032 | -0.067 | |
| LexSimModel=Llama3-70B2026.04 | -0.034 | -0.071 | |
| SCNModel=Llama3-70B2026.04 | -0.038 | -0.08 | |
| KLEModel=Llama3-70B2026.04 | -0.04 | -0.082 | |
| SPUQModel=Llama3-70B2026.04 | -0.041 | -0.085 | |
| LUQModel=Llama3-70B2026.04 | -0.042 | -0.089 | |
| EccModel=Qwen2.5-32B2026.04 | -0.07 | -0.048 | |
| EccModel=GPT-4.1-mini2026.04 | -0.082 | -0.084 | |
| DegModel=Qwen2.5-32B2026.04 | -0.105 | -0.071 | |
| DegModel=GPT-4.1-mini2026.04 | -0.122 | -0.125 | |
| LUQ-AtomicModel=Llama3-70B2026.04 | -0.128 | -0.169 | |
| SEModel=Qwen2.5-32B2026.04 | -0.131 | -0.089 | |
| LexSimModel=Qwen2.5-32B2026.04 | -0.14 | -0.095 | |
| SCNModel=Qwen2.5-32B2026.04 | -0.158 | -0.107 | |
| KLEModel=Qwen2.5-32B2026.04 | -0.162 | -0.112 | |
| LexSimModel=GPT-4.1-mini2026.04 | -0.163 | -0.167 | |
| SPUQModel=Qwen2.5-32B2026.04 | -0.168 | -0.115 | |
| LUQModel=Qwen2.5-32B2026.04 | -0.175 | -0.119 | |
| AGSCModel=Llama3-70B2026.04 | -0.175 | -0.229 | |
| LUQ-PairModel=Llama3-70B2026.04 | -0.178 | -0.069 | |
| SCNModel=GPT-4.1-mini2026.04 | -0.184 | -0.188 | |
| KLEModel=GPT-4.1-mini2026.04 | -0.19 | -0.195 | |
| SPUQModel=GPT-4.1-mini2026.04 | -0.195 | -0.201 | |
| LUQModel=GPT-4.1-mini2026.04 | -0.204 | -0.209 | |
| LUQ-AtomicModel=Qwen2.5-32B2026.04 | -0.255 | -0.175 | |
| LUQ-PairModel=Qwen2.5-32B2026.04 | -0.288 | -0.203 | |
| AGSCModel=Qwen2.5-32B2026.04 | -0.291 | -0.256 | |
| LUQ-PairModel=GPT-4.1-mini2026.04 | -0.324 | -0.298 | |
| LUQ-AtomicModel=GPT-4.1-mini2026.04 | -0.327 | -0.445 | |
| AGSCModel=GPT-4.1-mini2026.04 | -0.37 | -0.461 |