Preference evaluation on Ultra-Real benchmark
43.1Win Rateπbias (rubric-based preference attack)
Evaluation results
| Method | Links | |
|---|---|---|
| πbias (rubric-based preference attack)Comparison=πbias vs. πseed, Training setting=Benchmark-only (B), Evaluator model=LLaMA-3-8B, Decoding strategy=Best-of-42026.02 | 43.1 | |
| πbias (rubric-based preference attack)Comparison=πbias vs. πseed, Training setting=Benchmark+Target (BT), Evaluator model=LLaMA-3-8B, Decoding strategy=Best-of-42026.02 | 39.7 |