Distribution Alignment on Gender (US) - Even
0.049MAEIFT
Evaluation Results
| Method | Links | |
|---|---|---|
| IFTModel=Llama-3.1-8B-Instruct2026.04 | 0.049 | |
| IFTModel=Qwen2.5-7B-Instruct2026.04 | 0.051 | |
| KL-Optimized Fine-TuningModel=Qwen2.5-1.5B-Instruct2026.04 | 0.054 | |
| KL-Optimized Fine-TuningModel=Qwen2.5-7B-Instruct2026.04 | 0.061 | |
| KL-Optimized Fine-TuningModel=Llama-3.2-1B-Instruct2026.04 | 0.075 | |
| IFTModel=Qwen2.5-1.5B-Instruct2026.04 | 0.08 | |
| IFTModel=Llama-3.2-1B-Instruct2026.04 | 0.086 | |
| KL-Optimized Fine-TuningModel=Llama-3.1-8B-Instruct2026.04 | 0.091 | |
| PE-ExplicitModel=Qwen2.5-1.5B-Instruct2026.04 | 0.22 | |
| PE-ExplicitModel=Llama-3.1-8B-Instruct2026.04 | 0.237 | |
| Zero-shotModel=Llama-3.2-1B-Instruct2026.04 | 0.269 | |
| Zero-shotModel=Qwen2.5-1.5B-Instruct2026.04 | 0.3 | |
| Zero-shotModel=Qwen2.5-7B-Instruct2026.04 | 0.306 | |
| PE-ExplicitModel=Llama-3.2-1B-Instruct2026.04 | 0.338 | |
| Zero-shotModel=Llama-3.1-8B-Instruct2026.04 | 0.356 | |
| PE-ExplicitModel=Qwen2.5-7B-Instruct2026.04 | 0.409 | |
| DPOModel=Qwen2.5-7B-Instruct2026.04 | 0.5 | |
| DPOModel=Qwen2.5-1.5B-Instruct2026.04 | 0.5 | |
| DPOModel=Llama-3.1-8B-Instruct2026.04 | 0.5 | |
| DPOModel=Llama-3.2-1B-Instruct2026.04 | 0.5 |