Approximating human responses on Pew Research Center ATP Survey Wave 92
0.091WDHuman
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| Human2024.07 | 0.091 | 0.411 | 0.641 | |
| Anthology (NA)Model=Llama-3-70B, Persona Conditioning=Anthology (NA), Persona Matching=greedy2024.07 | 0.313 | 0.973 | 0.65 | |
| Anthology (NA)Model=Llama-3-70B, Persona Conditioning=Anthology (NA), Persona Matching=max weight2024.07 | 0.337 | 1.045 | 0.637 | |
| BioModel=Llama-3-70B, Persona Conditioning=Bio, Persona Matching=n/a2024.07 | 0.348 | 1.073 | 0.588 | |
| BioModel=Mixtral-8x22B, Persona Conditioning=Bio, Persona Matching=n/a2024.07 | 0.359 | 0.851 | 0.667 | |
| QAModel=Llama-3-70B, Persona Conditioning=QA, Persona Matching=n/a2024.07 | 0.371 | 1.032 | 0.664 | |
| Anthology (DP)Model=Mixtral-8x22B, Persona Conditioning=Anthology (DP), Persona Matching=n/a2024.07 | 0.378 | 0.531 | 0.624 | |
| Anthology (NA)Model=Mixtral-8x22B, Persona Conditioning=Anthology (NA), Persona Matching=greedy2024.07 | 0.392 | 0.981 | 0.627 | |
| Anthology (NA)Model=Mixtral-8x22B, Persona Conditioning=Anthology (NA), Persona Matching=max weight2024.07 | 0.408 | 0.846 | 0.61 | |
| Anthology (DP)Model=Llama-3-70B, Persona Conditioning=Anthology (DP), Persona Matching=n/a2024.07 | 0.419 | 0.965 | 0.636 | |
| QAModel=Mixtral-8x22B, Persona Conditioning=QA, Persona Matching=n/a2024.07 | 0.429 | 0.911 | 0.599 |