Prompt Extraction on IHEval Prompt Extraction Alignment 1.0
83.7AccuracyLlama3.1-8B-NSHA-DPO
Evaluation results
| Method | Links | |
|---|---|---|
| Llama3.1-8B-NSHA-DPOBackbone=Llama3.1-8B, Methodology=NSHA-DPO2026.04 | 83.7 | |
| Llama3.1-8B-NSBackbone=Llama3.1-8B, Methodology=Neuro-Symbolic2026.04 | 68.5 | |
| Qwen3-4B-it-NSBackbone=Qwen3-4B, Methodology=Neuro-Symbolic2026.04 | 65.1 | |
| Qwen3-4B-it-NSHA-DPOBackbone=Qwen3-4B, Methodology=NSHA-DPO2026.04 | 65.1 | |
| Llama3.1-8B-NSHA-HCALBackbone=Llama3.1-8B, Methodology=NSHA-HCAL2026.04 | 65.1 | |
| Qwen3-4B-itBackbone=Qwen3-4B, Methodology=Instruct2026.04 | 64.8 | |
| Llama3.1-8BBackbone=Llama3.1-8B, Methodology=Instruct2026.04 | 64.5 | |
| Qwen3-4B-it-NSHA-HCALBackbone=Qwen3-4B, Methodology=NSHA-HCAL2026.04 | 62.6 | |
| Llama3.1-8B-CoTBackbone=Llama3.1-8B, Methodology=Chain-of-Thought2026.04 | 60.1 | |
| Qwen3-4B-it-CoTBackbone=Qwen3-4B, Methodology=Chain-of-Thought2026.04 | 58.8 | |
| Qwen3-4B-it-NSHA-SFTBackbone=Qwen3-4B, Methodology=NSHA-SFT2026.04 | 49.7 | |
| Llama3.1-8B-NSHA-SFTBackbone=Llama3.1-8B, Methodology=NSHA-SFT2026.04 | 34.6 |