Preference Estimation on Sports car dataset Empirical Setting II m=200
469.25Beta_A EstimateGPT-4o
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| GPT-4oPrompt=Basic2024.12 | 469.25 | 207.47 | -7.03 | 0.0002 | |
| GPT-4oPrompt=CoT2024.12 | 352.96 | 178.51 | -6.26 | 0.0001 | |
| GPT-4o Fine-tunedPrompt=Basic2024.12 | 249.93 | 110.3 | -6.99 | 0.0004 | |
| GPT-4Prompt=CoT2024.12 | 221.32 | 121.56 | -6.62 | 0.0007 | |
| GPT-4oPrompt=FS2024.12 | 201.31 | 84.7 | -4.38 | 0.019 | |
| GPT-3.5-Turbo-0613Prompt=CoT2024.12 | 196.8 | 119.07 | -5.39 | 0.0005 | |
| GPT-3.5-Turbo-0125Prompt=CoT2024.12 | 177.78 | 113.93 | -6.64 | 0.0003 | |
| GPT-3.5-Turbo-0125Prompt=Basic2024.12 | 77.68 | 34.69 | -6.59 | 0.0002 | |
| GPT-4Prompt=Basic2024.12 | 35.55 | 19.68 | -4.72 | 0.0002 | |
| GPT-3.5-Turbo-0613Prompt=Basic2024.12 | 30.71 | 8.26 | -7.09 | 0.0001 |