Uncertainty Quantification on Countdown
0.61ROC-AUC (128)DiSE
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| DiSEBackbone=LLaDA-1.5-8B2026.03 | 0.61 | 0.471 | 0.586 | |
| MCBackbone=LLaDA-1.5-8B, Nmc=322026.03 | 0.608 | 0.557 | 0.52 | |
| LLaMA perplexityBackbone=LLaDA-1.5-8B, Evaluation Model=LLaMA3-Instruct-8B2026.03 | 0.596 | 0.459 | 0.362 | |
| MCBackbone=LLaDA-Instruct-8B, Nmc=322026.03 | 0.595 | 0.534 | 0.558 | |
| DiSEBackbone=LLaDA-Instruct-8B2026.03 | 0.578 | 0.521 | 0.622 | |
| LLaMA perplexityBackbone=LLaDA-Instruct-8B, Evaluation Model=LLaMA3-Instruct-8B2026.03 | 0.574 | 0.419 | 0.392 | |
| MCBackbone=LLaDA-1.5-8B, Nmc=12026.03 | 0.525 | 0.588 | 0.528 | |
| MCBackbone=LLaDA-Instruct-8B, Nmc=12026.03 | 0.524 | 0.52 | 0.528 |