Hate Speech Detection on Ethos (test)
0.937AccuracyUNIPROMPT
Evaluation results
| Method | Links | |
|---|---|---|
| UNIPROMPTSolver Model=GPT-3.5-Turbo, Evaluation Setting=zero-shot, Prompt Initialization=Task Description, Search Strategy=Greedy2024.06 | 0.937 | |
| UNIPROMPTSolver Model=GPT-3.5-Turbo, Evaluation Setting=zero-shot, Prompt Initialization=Task Description, Search Strategy=Beam2024.06 | 0.923 | |
| DSPy (BootstrapFewShotWithRandomSearch)Solver Model=GPT-3.5-Turbo, Evaluation Setting=few-shot2024.06 | 0.866 | |
| DSPy (MIPRO v2)Solver Model=GPT-3.5-Turbo, Evaluation Setting=few-shot2024.06 | 0.84 | |
| EvoPromptSolver Model=GPT-3.5-Turbo, Evaluation Setting=zero-shot2024.06 | 0.816 | |
| DSPy (MIPRO v2)Solver Model=GPT-3.5-Turbo, Evaluation Setting=zero-shot2024.06 | 0.797 | |
| TextGradSolver Model=GPT-3.5-Turbo, Evaluation Setting=zero-shot2024.06 | 0.795 | |
| Task DescriptionSolver Model=GPT-3.5-Turbo, Evaluation Setting=zero-shot2024.06 | 0.768 | |
| ProTeGiSolver Model=GPT-3.5-Turbo, Evaluation Setting=zero-shot2024.06 | 0.76 | |
| Expert PromptSolver Model=GPT-3.5-Turbo, Evaluation Setting=zero-shot2024.06 | 0.741 | |
| Llama PromptSolver Model=GPT-3.5-Turbo, Evaluation Setting=zero-shot, Reference=Section 3.22024.06 | 0.74 | |
| CoTSolver Model=GPT-3.5-Turbo, Evaluation Setting=zero-shot2024.06 | 0.72 | |
| OPROSolver Model=GPT-3.5-Turbo, Evaluation Setting=zero-shot2024.06 | 0.654 | |
| EvokeSolver Model=GPT-3.5-Turbo, Evaluation Setting=zero-shot2024.06 | 0.635 |