Rejection Accuracy Evaluation on Average across all datasets (test)
0.612G-NLLG-NLL
Evaluation Results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| G-NLLArchitecture=State-Space, Language Model=7b, Training Stage (PT/IT)=PT, Generation Length (short/long)=short, Correctness Scoring Rule (F1/LLM/LLM-Instruct)=F12024.12 | 0.612 | — | — | — | — | — | |
| G-NLLArchitecture=State-Space, Language Model=7b, Training Stage (PT/IT)=IT, Generation Length (short/long)=short, Correctness Scoring Rule (F1/LLM/LLM-Instruct)=F12024.12 | 0.615 | — | — | — | — | — | |
| G-NLLArchitecture=Transformer, Language Model=8b, Training Stage (PT/IT)=PT, Generation Length (short/long)=long, Correctness Scoring Rule (F1/LLM/LLM-Instruct)=LLM2024.12 | 0.619 | — | — | — | — | — | |
| G-NLLArchitecture=State-Space, Language Model=7b, Training Stage (PT/IT)=PT, Generation Length (short/long)=long, Correctness Scoring Rule (F1/LLM/LLM-Instruct)=LLM2024.12 | 0.623 | — | — | — | — | — | |
| G-NLLArchitecture=State-Space, Language Model=7b, Training Stage (PT/IT)=IT, Generation Length (short/long)=long, Correctness Scoring Rule (F1/LLM/LLM-Instruct)=LLM2024.12 | 0.625 | — | — | — | — | — | |
| G-NLLArchitecture=State-Space, Language Model=7b, Training Stage (PT/IT)=PT, Generation Length (short/long)=long, Correctness Scoring Rule (F1/LLM/LLM-Instruct)=LLM-Instruct2024.12 | 0.633 | — | — | — | — | — | |
| G-NLLArchitecture=State-Space, Language Model=7b, Training Stage (PT/IT)=PT, Generation Length (short/long)=short, Correctness Scoring Rule (F1/LLM/LLM-Instruct)=LLM-Instruct2024.12 | 0.651 | — | — | — | — | — | |
| G-NLLArchitecture=Transformer, Language Model=8b, Training Stage (PT/IT)=IT, Generation Length (short/long)=long, Correctness Scoring Rule (F1/LLM/LLM-Instruct)=LLM2024.12 | 0.652 | — | — | — | — | — | |
| G-NLLArchitecture=State-Space, Language Model=7b, Training Stage (PT/IT)=IT, Generation Length (short/long)=short, Correctness Scoring Rule (F1/LLM/LLM-Instruct)=LLM-Instruct2024.12 | 0.653 | — | — | — | — | — | |
| G-NLLArchitecture=State-Space, Language Model=7b, Training Stage (PT/IT)=IT, Generation Length (short/long)=long, Correctness Scoring Rule (F1/LLM/LLM-Instruct)=LLM-Instruct2024.12 | 0.658 | — | — | — | — | — | |
| G-NLLArchitecture=Transformer, Language Model=8b, Training Stage (PT/IT)=PT, Generation Length (short/long)=short, Correctness Scoring Rule (F1/LLM/LLM-Instruct)=F12024.12 | 0.681 | — | — | — | — | — | |
| G-NLLArchitecture=Transformer, Language Model=8b, Training Stage (PT/IT)=PT, Generation Length (short/long)=long, Correctness Scoring Rule (F1/LLM/LLM-Instruct)=LLM-Instruct2024.12 | 0.686 | — | — | — | — | — | |
| G-NLLArchitecture=Transformer, Language Model=8b, Training Stage (PT/IT)=IT, Generation Length (short/long)=short, Correctness Scoring Rule (F1/LLM/LLM-Instruct)=F12024.12 | 0.702 | — | — | — | — | — | |
| G-NLLArchitecture=Transformer, Language Model=70b, Training Stage (PT/IT)=IT, Generation Length (short/long)=long, Correctness Scoring Rule (F1/LLM/LLM-Instruct)=LLM2024.12 | 0.715 | — | — | — | — | — | |
| G-NLLArchitecture=Transformer, Language Model=8b, Training Stage (PT/IT)=PT, Generation Length (short/long)=short, Correctness Scoring Rule (F1/LLM/LLM-Instruct)=LLM-Instruct2024.12 | 0.723 | — | — | — | — | — | |
| G-NLLArchitecture=Transformer, Language Model=70b, Training Stage (PT/IT)=PT, Generation Length (short/long)=long, Correctness Scoring Rule (F1/LLM/LLM-Instruct)=LLM2024.12 | 0.724 | — | — | — | — | — | |
| G-NLLLanguage Model=Average2024.12 | 0.729 | — | — | — | — | — | |
| G-NLLArchitecture=Transformer, Language Model=8b, Training Stage (PT/IT)=IT, Generation Length (short/long)=long, Correctness Scoring Rule (F1/LLM/LLM-Instruct)=LLM-Instruct2024.12 | 0.734 | — | — | — | — | — | |
| G-NLLArchitecture=State-Space, Language Model=7b, Training Stage (PT/IT)=PT, Generation Length (short/long)=short, Correctness Scoring Rule (F1/LLM/LLM-Instruct)=LLM2024.12 | 0.742 | — | — | — | — | — | |
| G-NLLArchitecture=State-Space, Language Model=7b, Training Stage (PT/IT)=IT, Generation Length (short/long)=short, Correctness Scoring Rule (F1/LLM/LLM-Instruct)=LLM2024.12 | 0.744 | — | — | — | — | — | |
| G-NLLArchitecture=Transformer, Language Model=8b, Training Stage (PT/IT)=IT, Generation Length (short/long)=short, Correctness Scoring Rule (F1/LLM/LLM-Instruct)=LLM-Instruct2024.12 | 0.751 | — | — | — | — | — | |
| G-NLLArchitecture=Transformer, Language Model=8b, Training Stage (PT/IT)=PT, Generation Length (short/long)=short, Correctness Scoring Rule (F1/LLM/LLM-Instruct)=LLM2024.12 | 0.778 | — | — | — | — | — | |
| G-NLLArchitecture=Transformer, Language Model=8b, Training Stage (PT/IT)=IT, Generation Length (short/long)=short, Correctness Scoring Rule (F1/LLM/LLM-Instruct)=LLM2024.12 | 0.788 | — | — | — | — | — | |
| G-NLLArchitecture=Transformer, Language Model=70b, Training Stage (PT/IT)=PT, Generation Length (short/long)=long, Correctness Scoring Rule (F1/LLM/LLM-Instruct)=LLM-Instruct2024.12 | 0.812 | — | — | — | — | — | |
| G-NLLArchitecture=Transformer, Language Model=70b, Training Stage (PT/IT)=IT, Generation Length (short/long)=short, Correctness Scoring Rule (F1/LLM/LLM-Instruct)=F12024.12 | 0.823 | — | — | — | — | — | |
| G-NLLArchitecture=Transformer, Language Model=70b, Training Stage (PT/IT)=PT, Generation Length (short/long)=short, Correctness Scoring Rule (F1/LLM/LLM-Instruct)=F12024.12 | 0.836 | — | — | — | — | — | |
| G-NLLArchitecture=Transformer, Language Model=70b, Training Stage (PT/IT)=IT, Generation Length (short/long)=short, Correctness Scoring Rule (F1/LLM/LLM-Instruct)=LLM2024.12 | 0.845 | — | — | — | — | — | |
| G-NLLArchitecture=Transformer, Language Model=70b, Training Stage (PT/IT)=IT, Generation Length (short/long)=long, Correctness Scoring Rule (F1/LLM/LLM-Instruct)=LLM-Instruct2024.12 | 0.851 | — | — | — | — | — | |
| G-NLLArchitecture=Transformer, Language Model=70b, Training Stage (PT/IT)=PT, Generation Length (short/long)=short, Correctness Scoring Rule (F1/LLM/LLM-Instruct)=LLM2024.12 | 0.855 | — | — | — | — | — | |
| G-NLLArchitecture=Transformer, Language Model=70b, Training Stage (PT/IT)=IT, Generation Length (short/long)=short, Correctness Scoring Rule (F1/LLM/LLM-Instruct)=LLM-Instruct2024.12 | 0.87 | — | — | — | — | — | |
| G-NLLArchitecture=Transformer, Language Model=70b, Training Stage (PT/IT)=PT, Generation Length (short/long)=short, Correctness Scoring Rule (F1/LLM/LLM-Instruct)=LLM-Instruct2024.12 | 0.881 | — | — | — | — | — | |
| D-SEArchitecture=Transformer, Language Model=8b, Training Stage (PT/IT)=PT, Generation Length (short/long)=short, Correctness Scoring Rule (F1/LLM/LLM-Instruct)=F12024.12 | — | — | — | — | — | 0.655 | |
| D-SELanguage Model=Average2024.12 | — | — | — | — | — | 0.718 | |
| LN-PEArchitecture=Transformer, Language Model=8b, Training Stage (PT/IT)=PT, Generation Length (short/long)=short, Correctness Scoring Rule (F1/LLM/LLM-Instruct)=F12024.12 | — | — | 0.672 | — | — | — | |
| LN-PELanguage Model=Average2024.12 | — | — | 0.72 | — | — | — | |
| LN-SEArchitecture=Transformer, Language Model=8b, Training Stage (PT/IT)=PT, Generation Length (short/long)=short, Correctness Scoring Rule (F1/LLM/LLM-Instruct)=F12024.12 | — | — | — | — | 0.643 | — | |
| LN-SELanguage Model=Average2024.12 | — | — | — | — | 0.71 | — | |
| PEArchitecture=Transformer, Language Model=8b, Training Stage (PT/IT)=PT, Generation Length (short/long)=short, Correctness Scoring Rule (F1/LLM/LLM-Instruct)=F12024.12 | — | 0.661 | — | — | — | — | |
| PELanguage Model=Average2024.12 | — | 0.712 | — | — | — | — | |
| SEArchitecture=Transformer, Language Model=8b, Training Stage (PT/IT)=PT, Generation Length (short/long)=short, Correctness Scoring Rule (F1/LLM/LLM-Instruct)=F12024.12 | — | — | — | 0.651 | — | — | |
| SELanguage Model=Average2024.12 | — | — | — | 0.711 | — | — |