Sentiment Analysis on FPB
85.78AccuracySC
Evaluation results
| Method | Links | |
|---|---|---|
| SCBackbone Model=Mistral, Shot Count=16-shot2025.05 | 85.78 | |
| SCModel=Mistral, k-shot=162025.05 | 85.78 | |
| DCBackbone Model=Llama, Shot Count=16-shot2025.05 | 85.23 | |
| DCModel=Llama, k-shot=162025.05 | 85.23 | |
| DCBackbone Model=Mistral, Shot Count=16-shot2025.05 | 85.08 | |
| DCModel=Mistral, k-shot=162025.05 | 85.08 | |
| Base LLMBackbone Model=Mistral, Shot Count=16-shot2025.05 | 83.91 | |
| Base LLMModel=Mistral, k-shot=162025.05 | 83.91 | |
| BCBackbone Model=Llama, Shot Count=16-shot2025.05 | 83.52 | |
| BCModel=Llama, k-shot=162025.05 | 83.52 | |
| CCBackbone Model=Llama, Shot Count=16-shot2025.05 | 82.34 | |
| CCModel=Llama, k-shot=162025.05 | 82.34 | |
| CCBackbone Model=Mistral, Shot Count=16-shot2025.05 | 82.03 | |
| CCModel=Mistral, k-shot=162025.05 | 82.03 | |
| Base LLMBackbone Model=Llama, Shot Count=16-shot2025.05 | 81.72 | |
| Base LLMModel=Llama, k-shot=162025.05 | 81.72 | |
| BCBackbone Model=Mistral, Shot Count=16-shot2025.05 | 81.25 | |
| BCModel=Mistral, k-shot=162025.05 | 81.25 | |
| SCBackbone Model=Llama, Shot Count=16-shot2025.05 | 78.83 | |
| SCModel=Llama, k-shot=162025.05 | 78.83 | |
| BCBackbone Model=Qwen, Shot Count=16-shot2025.05 | 72.81 | |
| BCModel=Qwen, k-shot=162025.05 | 72.81 | |
| SCBackbone Model=Qwen, Shot Count=16-shot2025.05 | 67.11 | |
| SCModel=Qwen, k-shot=162025.05 | 67.11 | |
| Latent Concept LearningLLM=GPT2 (124M)2023.01 | 64.5 | |
| Latent Concept LearningLLM=GPT3-b (1.3B)2023.01 | 64.3 | |
| Latent Concept LearningLLM=GPT3-c (6.7B)2023.01 | 64.1 | |
| Base LLMBackbone Model=Qwen, Shot Count=16-shot2025.05 | 64.06 | |
| Base LLMModel=Qwen, k-shot=162025.05 | 64.06 | |
| Latent Concept LearningLLM=GPT3-d (175B)2023.01 | 62.7 | |
| SimilarLLM=GPT3-c (6.7B)2023.01 | 62.2 | |
| Latent Concept LearningLLM=GPT2-xl (1.5B)2023.01 | 62 | |
| Latent Concept LearningLLM=GPT3-a (350M)2023.01 | 61.9 | |
| Latent Concept LearningLLM=GPT2-l (774M)2023.01 | 60.4 | |
| Latent Concept LearningLLM=GPT2-m (355M)2023.01 | 59.3 | |
| UniformLLM=GPT3-d (175B)2023.01 | 59.2 | |
| SimilarLLM=GPT2-m (355M)2023.01 | 57.7 | |
| UniformLLM=GPT3-a (350M)2023.01 | 56.6 | |
| SimilarLLM=GPT3-b (1.3B)2023.01 | 56.2 | |
| SimilarLLM=GPT2 (124M)2023.01 | 55.9 | |
| SimilarLLM=GPT3-d (175B)2023.01 | 55.4 | |
| UniformLLM=GPT3-b (1.3B)2023.01 | 55.2 | |
| SimilarLLM=GPT2-l (774M)2023.01 | 54.8 | |
| UniformLLM=GPT2-xl (1.5B)2023.01 | 53.2 | |
| SimilarLLM=GPT2-xl (1.5B)2023.01 | 53 | |
| UniformLLM=GPT2 (124M)2023.01 | 52.9 | |
| UniformLLM=GPT3-c (6.7B)2023.01 | 52.6 | |
| SimilarLLM=GPT3-a (350M)2023.01 | 52.2 | |
| UniformLLM=GPT2-m (355M)2023.01 | 52 | |
| UniformLLM=GPT2-l (774M)2023.01 | 51.3 | |
| BloombergGPT2023.03 | 51.07 | |
| BLOOM176B2023.03 | 50.25 | |
| 5x HumanNumber of Human Annotations=1000, Number of GPT-3.5 Annotations=02023.10 | 49.24 | |
| OPT66B2023.03 | 48.67 | |
| IMFLNumber of Human Annotations=200, Number of GPT-3.5 Annotations=8002023.10 | 47.88 | |
| 4x HumanNumber of Human Annotations=800, Number of GPT-3.5 Annotations=02023.10 | 47.32 | |
| GPT-NeoX2023.03 | 44.64 | |
| 3x HumanNumber of Human Annotations=600, Number of GPT-3.5 Annotations=02023.10 | 43.16 | |
| 2x HumanNumber of Human Annotations=400, Number of GPT-3.5 Annotations=02023.10 | 40.23 | |
| All GPT-3.5Number of Human Annotations=0, Number of GPT-3.5 Annotations=10002023.10 | 39.53 | |
| 1x HumanNumber of Human Annotations=200, Number of GPT-3.5 Annotations=02023.10 | 38.74 | |
| DCBackbone Model=Qwen, Shot Count=16-shot2025.05 | 37.03 | |
| DCModel=Qwen, k-shot=162025.05 | 37.03 | |
| CCBackbone Model=Qwen, Shot Count=16-shot2025.05 | 25.08 | |
| CCModel=Qwen, k-shot=162025.05 | 25.08 |