Answer Plausibility Estimation on MuSiQue
1.0888Cohen's dEntropy-Plausibility
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Entropy-PlausibilityCategory=Q-DAPS2026.05 | 1.0888 | -0.9001 | |
| LLaMA 3.3 70bCategory=Uncertainty-based2026.05 | 0.4219 | -0.5518 | |
| LLaMA 3.3 70bCategory=Prompt-based2026.05 | 0.2453 | -0.109 | |
| LLaMA 3.1 8bCategory=Uncertainty-based2026.05 | 0.1365 | -0.3815 | |
| Retrieval ComplexityCategory=Retriever-based2026.05 | 0.1284 | -0.3451 | |
| PopQACategory=Popularity2026.05 | -0.0275 | 0.2818 | |
| Avg-PlausibilityCategory=Q-DAPS2026.05 | -0.2242 | 0.0272 | |
| Gunning-FogCategory=Readability2026.05 | -0.3947 | 0.7181 | |
| LLaMA 3.1 8bCategory=Prompt-based2026.05 | -0.535 | 0.2636 | |
| Flesch-KincaidCategory=Readability2026.05 | -0.543 | 0.5545 |