Closed-book Question Answering on Ever Young
81.67LLM ScoreKNN
Evaluation results
| Method | Links | |
|---|---|---|
| KNNInference Tokens (input / output) - Base Model=3321 / 4342026.04 | 81.67 | |
| Fine-tuningTrain Tokens (input / output) - Base Model=36250 / 5945, Inference Tokens (input / output) - Base Model=2123 / 3192026.04 | 72.08 | |
| DSPy GEPATrain Tokens (input / output) - Base Model=1098892 / 15248, Train Tokens (input / output) - Reflection Model=118233 / 88819, Inference Tokens (input / output) - Base Model=58193 / 6232026.04 | 50.83 | |
| Initial promptInference Tokens (input / output) - Base Model=2123 / 6082026.04 | 42.08 | |
| AIRTrain Tokens (input / output) - Embed Model=3878 / -, Train Tokens (input / output) - Base Model=123152 / 2281, Train Tokens (input / output) - Reflection Model=19665 / 31183, Inference Tokens (input / output) - Base Model=68063 / 3822026.04 | 42.08 | |
| DSPy BootstrapFewShot (#10)Train Tokens (input / output) - Base Model=7275 / 223, Inference Tokens (input / output) - Base Model=21983 / 5922026.04 | 38.3 | |
| DSPy MIPROv2Train Tokens (input / output) - Base Model=906850 / 74221, Inference Tokens (input / output) - Base Model=14573 / 6042026.04 | 37.5 | |
| TextGradTrain Tokens (input / output) - Base Model=405807 / 2925, Train Tokens (input / output) - Reflection Model=601023 / 684425, Inference Tokens (input / output) - Base Model=127373 / 3562026.04 | 37.5 |