Personality Induction on Big-Five Personality Induction With Questionnaires
9.38Accuracy (S1)gemma-7b
Evaluation results
| Method | Links | ||
|---|---|---|---|
| gemma-7bFine-tuning paradigm=Base2026.05 | 9.38 | 3 | |
| gemma-7bFine-tuning paradigm=SFT2026.05 | 6.25 | 2 | |
| llama-3.2-3bFine-tuning paradigm=SFT2026.05 | 6.25 | 2 | |
| llama-3.1-8bFine-tuning paradigm=Base2026.05 | 6.25 | 2 | |
| llama-3.1-8bFine-tuning paradigm=DPO2026.05 | 6.25 | 2 | |
| llama-3.1-8bFine-tuning paradigm=ORPO2026.05 | 6.25 | 2 | |
| GPT-3.5Fine-tuning paradigm=SFT2026.05 | 6.25 | 2 | |
| gemma-2-2bFine-tuning paradigm=Base2026.05 | 3.13 | 1 | |
| gemma-2-2bFine-tuning paradigm=SFT2026.05 | 3.13 | 1 | |
| gemma-7bFine-tuning paradigm=DPO2026.05 | 3.13 | 1 | |
| gemma-7bFine-tuning paradigm=ORPO2026.05 | 3.13 | 1 | |
| llama-3.2-3bFine-tuning paradigm=DPO2026.05 | 3.13 | 1 | |
| llama-3.2-3bFine-tuning paradigm=ORPO2026.05 | 3.13 | 1 | |
| llama-3.1-8bFine-tuning paradigm=SFT2026.05 | 3.13 | 1 | |
| GPT-3.5Fine-tuning paradigm=Base2026.05 | 3.13 | 1 | |
| gemma-2-2bFine-tuning paradigm=DPO2026.05 | 0 | 0 | |
| gemma-2-2bFine-tuning paradigm=ORPO2026.05 | 0 | 0 | |
| llama-3.2-3bFine-tuning paradigm=Base2026.05 | 0 | 0 |