Alignment on TruthfulQA MC2
77.72ScoreQwen3-14B
Evaluation results
| Method | Links | |
|---|---|---|
| Qwen3-14BModel Scale=14B, NGM Configuration=False, Decoding Settings=identical decoding settings2026.05 | 77.72 | |
| Qwen3-14B + NGMModel Scale=14B, NGM Configuration=True, Decoding Settings=identical decoding settings2026.05 | 77.6 | |
| Qwen3-8B + NGMModel Scale=8B, NGM Configuration=True, Decoding Settings=identical decoding settings2026.05 | 76.38 | |
| Qwen3-8BModel Scale=8B, NGM Configuration=False, Decoding Settings=identical decoding settings2026.05 | 76.13 | |
| Qwen3-1.7B + NGMModel Scale=1.7B, NGM Configuration=True, Decoding Settings=identical decoding settings2026.05 | 52.51 | |
| Qwen3-1.7BModel Scale=1.7B, NGM Configuration=False, Decoding Settings=identical decoding settings2026.05 | 52.39 | |
| Qwen3-4B + NGMModel Scale=4B, NGM Configuration=True, Decoding Settings=identical decoding settings2026.05 | 35.37 | |
| Qwen3-4BModel Scale=4B, NGM Configuration=False, Decoding Settings=identical decoding settings2026.05 | 35.25 | |
| Qwen3-0.6B + NGMModel Scale=0.6B, NGM Configuration=True, Decoding Settings=identical decoding settings2026.05 | 18.48 | |
| Qwen3-0.6BModel Scale=0.6B, NGM Configuration=False, Decoding Settings=identical decoding settings2026.05 | 14.81 |