Utility Judgment on GTI-NQ
76.34F1 ScoreITEM-ARs-ExpA
Evaluation Results
| Method | Links | |
|---|---|---|
| ITEM-ARs-ExpALLM=ChatGPT, Approach=Listwise, m-value=32024.06 | 76.34 | |
| ITEM-ARs-ExpALLM=ChatGPT, Approach=Listwise, m-value=12024.06 | 74.43 | |
| ITEM-As-ExpALLM=ChatGPT, Approach=Listwise, m-value=32024.06 | 73.55 | |
| ITEM-As-ExpALLM=ChatGPT, Approach=Listwise, m-value=12024.06 | 72.44 | |
| k-samplingLLM=ChatGPT, Approach=Listwise2024.06 | 71.17 | |
| ITEM-As-ImpLLM=ChatGPT, Approach=Listwise, m-value=32024.06 | 69.68 | |
| ITEM-As-ImpLLM=ChatGPT, Approach=Listwise, m-value=12024.06 | 68.92 | |
| UJ-ExapALLM=ChatGPT, Approach=Listwise2024.06 | 66.13 | |
| VanillaLLM=ChatGPT, Approach=Listwise2024.06 | 59.37 | |
| UJ-ImpALLM=ChatGPT, Approach=Listwise2024.06 | 57.4 | |
| ITEM-As-ExpALLM=ChatGPT, Approach=Pointwise, m-value=32024.06 | 55.45 | |
| ITEM-As-ExpALLM=ChatGPT, Approach=Pointwise, m-value=12024.06 | 54.89 | |
| ITEM-ARs-ExpALLM=Llama3-8B, Approach=Listwise, m-value=32024.06 | 51.22 | |
| ITEM-ARs-ExpALLM=Llama3-8B, Approach=Listwise, m-value=12024.06 | 50.77 | |
| ITEM-As-ExpALLM=Llama3-8B, Approach=Listwise, m-value=32024.06 | 49.73 | |
| ITEM-As-ExpALLM=Llama3-8B, Approach=Listwise, m-value=12024.06 | 49.26 | |
| k-samplingLLM=Llama3-8B, Approach=Listwise2024.06 | 49.2 | |
| ITEM-As-ExpALLM=Llama3-8B, Approach=Pointwise, m-value=32024.06 | 48.9 | |
| ITEM-As-ImpLLM=Llama3-8B, Approach=Listwise, m-value=32024.06 | 48.03 | |
| ITEM-As-ExpALLM=Llama3-8B, Approach=Pointwise, m-value=12024.06 | 47.52 | |
| ITEM-As-ImpLLM=Llama3-8B, Approach=Listwise, m-value=12024.06 | 47.47 | |
| UJ-ExapALLM=Llama3-8B, Approach=Listwise2024.06 | 47.07 | |
| ITEM-As-ImpLLM=ChatGPT, Approach=Pointwise, m-value=32024.06 | 43.58 | |
| VanillaLLM=Llama3-8B, Approach=Listwise2024.06 | 43.38 | |
| UJ-ImpALLM=Llama3-8B, Approach=Listwise2024.06 | 43.31 | |
| ITEM-As-ImpLLM=ChatGPT, Approach=Pointwise, m-value=12024.06 | 43.17 | |
| UJ-ExapALLM=Llama3-8B, Approach=Pointwise2024.06 | 39.32 | |
| UJ-ImpALLM=Llama3-8B, Approach=Pointwise2024.06 | 38.72 | |
| ITEM-As-ImpLLM=Llama3-8B, Approach=Pointwise, m-value=32024.06 | 38.34 | |
| ITEM-As-ImpLLM=Llama3-8B, Approach=Pointwise, m-value=12024.06 | 37.98 | |
| UJ-ImpALLM=ChatGPT, Approach=Pointwise2024.06 | 37.29 | |
| UJ-ExapALLM=ChatGPT, Approach=Pointwise2024.06 | 37.17 | |
| VanillaLLM=ChatGPT, Approach=Pointwise2024.06 | 35.31 | |
| VanillaLLM=Llama3-8B, Approach=Pointwise2024.06 | 28.55 |