Detection on TweetEval-hate
67.53Macro F1SC
Evaluation Results
| Method | Links | |
|---|---|---|
| SCModel=Mistral, Shots=8-shot2025.05 | 67.53 | |
| BCModel=Mistral, Shots=8-shot2025.05 | 63.25 | |
| GPT-J (DC)Backbone=GPT-J, Prompting=DC, Shots=8-shot2023.05 | 61.2 | |
| Base LLMModel=Mistral, Shots=8-shot2025.05 | 59.55 | |
| GPT-3 (DC)Backbone=GPT-3, Prompting=DC, Shots=8-shot2023.05 | 59 | |
| SCModel=Qwen, Shots=8-shot2025.05 | 53.63 | |
| BCModel=Llama, Shots=8-shot2025.05 | 53.59 | |
| GPT-3 (CC)Backbone=GPT-3, Prompting=CC, Shots=8-shot2023.05 | 49.5 | |
| SCModel=Llama, Shots=8-shot2025.05 | 48.05 | |
| Base LLMModel=Llama, Shots=8-shot2025.05 | 39.86 | |
| Base LLMModel=Qwen, Shots=8-shot2025.05 | 38.01 | |
| BCModel=Qwen, Shots=8-shot2025.05 | 38.01 | |
| GPT-3 (Original)Backbone=GPT-3, Prompting=Original, Shots=8-shot2023.05 | 36.8 | |
| GPT-J (CC)Backbone=GPT-J, Prompting=CC, Shots=8-shot2023.05 | 36.4 | |
| GPT-J (Original)Backbone=GPT-J, Prompting=Original, Shots=8-shot2023.05 | 32.8 | |
| CCModel=Qwen, Shots=8-shot2025.05 | 27.89 | |
| DCModel=Qwen, Shots=8-shot2025.05 | 27.89 | |
| CCModel=Llama, Shots=8-shot2025.05 | 27.89 | |
| DCModel=Llama, Shots=8-shot2025.05 | 27.89 | |
| CCModel=Mistral, Shots=8-shot2025.05 | 27.89 | |
| DCModel=Mistral, Shots=8-shot2025.05 | 27.89 |