Sentiment Analysis on Sentiment140
94.7Mean AccuracyGENICL
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| GENICLBackbone=LLaMA-7B, Evaluation Setting=Few-shot (ICL)2025.05 | 94.7 | — | — | |
| SBERTBackbone=LLaMA-7B, Evaluation Setting=Few-shot (ICL)2025.05 | 94.1 | — | — | |
| E5baseBackbone=LLaMA-7B, Evaluation Setting=Few-shot (ICL)2025.05 | 93 | — | — | |
| CBDSBackbone=LLaMA-7B, Evaluation Setting=Few-shot (ICL)2025.05 | 92.5 | — | — | |
| LLM-RBackbone=LLaMA-7B, Evaluation Setting=Few-shot (ICL)2025.05 | 91.6 | — | — | |
| EPRBackbone=LLaMA-7B, Evaluation Setting=Few-shot (ICL)2025.05 | 91.4 | — | — | |
| BM25Backbone=LLaMA-7B, Evaluation Setting=Few-shot (ICL)2025.05 | 88.3 | — | — | |
| RandomBackbone=LLaMA-7B, Evaluation Setting=Few-shot (ICL)2025.05 | 78.8 | — | — | |
| AlignInsAttack type=Badnet2025.03 | 69.26 | 41.43 | 58.57 | |
| FedAvg*Attack type=Badnet, Note=Perfectly robust version2025.03 | 67.31 | 41.57 | 58.43 | |
| FedAvgAttack type=Badnet2025.03 | 66.16 | 85.55 | 14.45 | |
| RFAAttack type=Badnet2025.03 | 60.71 | 99.9 | 0.1 | |
| RLRAttack type=Badnet2025.03 | 51.23 | 99.05 | 0.95 | |
| Zero-shotBackbone=LLaMA-7B, Evaluation Setting=Zero-shot2025.05 | 49.3 | — | — |