Sentiment Analysis on Rotten Tomatoes (RT)
93.42Macro-F1DC
Evaluation Results
| Method | Links | |
|---|---|---|
| DCModel=Qwen, k-shot=162025.05 | 93.42 | |
| CCModel=Qwen, k-shot=162025.05 | 93.32 | |
| CCModel=Mistral, k-shot=162025.05 | 92.93 | |
| CCModel=Llama, k-shot=162025.05 | 92.78 | |
| DCModel=Mistral, Shots=8-shot2025.05 | 92.7 | |
| CCModel=Mistral, Shots=8-shot2025.05 | 92.69 | |
| BCModel=Qwen, k-shot=162025.05 | 92.64 | |
| BCModel=Mistral, Shots=8-shot2025.05 | 92.62 | |
| Base LLMModel=Mistral, Shots=8-shot2025.05 | 92.61 | |
| SCModel=Llama, Shots=8-shot2025.05 | 92.53 | |
| DCModel=Llama, Shots=8-shot2025.05 | 92.47 | |
| DCModel=Llama, k-shot=162025.05 | 92.47 | |
| BCModel=Llama, k-shot=162025.05 | 92.46 | |
| BCModel=Mistral, k-shot=162025.05 | 92.46 | |
| CCModel=Llama, Shots=8-shot2025.05 | 92.4 | |
| Base LLMModel=Mistral, k-shot=162025.05 | 92.39 | |
| CCModel=Qwen, Shots=8-shot2025.05 | 92.3 | |
| SCModel=Qwen, k-shot=162025.05 | 92.15 | |
| DCModel=Mistral, k-shot=162025.05 | 92.15 | |
| BCModel=Llama, Shots=8-shot2025.05 | 92.01 | |
| Base LLMModel=Llama, k-shot=162025.05 | 92.01 | |
| BCModel=Qwen, Shots=8-shot2025.05 | 91.95 | |
| Base LLMModel=Llama, Shots=8-shot2025.05 | 91.94 | |
| SCModel=Llama, k-shot=162025.05 | 91.83 | |
| Base LLMModel=Qwen, k-shot=162025.05 | 91.56 | |
| DCModel=Qwen, Shots=8-shot2025.05 | 91.09 | |
| SCModel=Mistral, k-shot=162025.05 | 91.07 | |
| Base LLMModel=Qwen, Shots=8-shot2025.05 | 91 | |
| SCModel=Qwen, Shots=8-shot2025.05 | 90.64 | |
| SCModel=Mistral, Shots=8-shot2025.05 | 90.09 |