Argument Persuasiveness Prediction on Anthropic
0.82RMSEMS-PS-MLP
Evaluation Results
| Method | Links | |
|---|---|---|
| MS-PS-MLPFramework=Multi-Stage Persuasion Strategy with MLP2026.01 | 0.82 | |
| Baseline-2Description=Refined prompt adjusted to improve the simpler prompt, Evaluation Model Averaging=Gemma-3-12B and OpenAI-o32026.01 | 1.44 | |
| Baseline-1Description=Basic prompt directly asking to predict the outcome, Evaluation Model Averaging=Gemma-3-12B and OpenAI-o32026.01 | 1.55 |