Question Answering on CQA (Client Model Specific)
43Accuracy (GPT-2-Small)FedCoLLM
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| FedCoLLM2024.11 | 43 | 60.8 | 57.7 | |
| FedAvg2024.11 | 41.7 | 58.6 | 56.8 | |
| Standalone2024.11 | 40.5 | 57.3 | 56.1 | |
| Zero-Shot2024.11 | 28.3 | 41.9 | 30.1 |
| Method | Links | |||
|---|---|---|---|---|
| FedCoLLM2024.11 | 43 | 60.8 | 57.7 | |
| FedAvg2024.11 | 41.7 | 58.6 | 56.8 | |
| Standalone2024.11 | 40.5 | 57.3 | 56.1 | |
| Zero-Shot2024.11 | 28.3 | 41.9 | 30.1 |