Question Selection and Generation on America in One Room: Democratic Reform (A1R)
1.68alpha_JRHuman
Evaluation Results
| Method | Links | |
|---|---|---|
| HumanN=50, k=7, multiple sibling questions=true2025.11 | 1.68 | |
| RandomN=54, k=8, multiple sibling questions=false2025.11 | 1.459 | |
| RandomN=50, k=7, multiple sibling questions=true2025.11 | 1.281 | |
| RandomN=57, k=7, multiple sibling questions=true2025.11 | 1.258 | |
| RandomN=65, k=8, multiple sibling questions=false2025.11 | 1.247 | |
| RandomN=61, k=8, multiple sibling questions=false2025.11 | 1.246 | |
| RandomN=56, k=7, multiple sibling questions=true2025.11 | 1.241 | |
| RandomN=57, k=8, multiple sibling questions=false2025.11 | 1.227 | |
| RandomN=48, k=7, multiple sibling questions=false2025.11 | 1.084 | |
| HumanN=61, k=8, multiple sibling questions=false2025.11 | 1.049 | |
| HumanN=54, k=8, multiple sibling questions=false2025.11 | 1.037 | |
| HumanN=48, k=7, multiple sibling questions=false2025.11 | 1.021 | |
| LLMN=48, k=7, multiple sibling questions=false2025.11 | 1.018 | |
| LLMN=54, k=8, multiple sibling questions=false2025.11 | 0.913 | |
| HumanN=56, k=7, multiple sibling questions=true2025.11 | 0.875 | |
| HumanN=57, k=8, multiple sibling questions=false2025.11 | 0.842 | |
| HumanN=57, k=7, multiple sibling questions=true2025.11 | 0.798 | |
| LLMN=57, k=8, multiple sibling questions=false2025.11 | 0.778 | |
| LLMN=65, k=8, multiple sibling questions=false2025.11 | 0.751 | |
| LLMN=61, k=8, multiple sibling questions=false2025.11 | 0.744 | |
| HumanN=65, k=8, multiple sibling questions=false2025.11 | 0.738 | |
| LLMN=56, k=7, multiple sibling questions=true2025.11 | 0.701 | |
| LLMbestN=48, k=7, multiple sibling questions=false2025.11 | 0.583 | |
| LLMN=57, k=7, multiple sibling questions=true2025.11 | 0.57 | |
| LLMN=50, k=7, multiple sibling questions=true2025.11 | 0.545 | |
| IPN=61, k=8, multiple sibling questions=false2025.11 | 0.525 | |
| IPN=65, k=8, multiple sibling questions=false2025.11 | 0.492 | |
| LLMbestN=54, k=8, multiple sibling questions=false2025.11 | 0.444 | |
| IPN=48, k=7, multiple sibling questions=false2025.11 | 0.438 | |
| IPN=57, k=8, multiple sibling questions=false2025.11 | 0.421 | |
| LLMbestN=57, k=8, multiple sibling questions=false2025.11 | 0.421 | |
| IPN=50, k=7, multiple sibling questions=true2025.11 | 0.42 | |
| LLMbestN=61, k=8, multiple sibling questions=false2025.11 | 0.393 | |
| IPN=56, k=7, multiple sibling questions=true2025.11 | 0.375 | |
| LLMbestN=56, k=7, multiple sibling questions=true2025.11 | 0.375 | |
| LLMbestN=65, k=8, multiple sibling questions=false2025.11 | 0.369 | |
| IPN=57, k=7, multiple sibling questions=true2025.11 | 0.368 | |
| LLMbestN=57, k=7, multiple sibling questions=true2025.11 | 0.368 | |
| IPN=54, k=8, multiple sibling questions=false2025.11 | 0.296 | |
| LLMbestN=50, k=7, multiple sibling questions=true2025.11 | 0.28 |