Response Generation on ESConv (test)
3.9FluencyFiSMiness
Evaluation results
| Method | Links | |||||||
|---|---|---|---|---|---|---|---|---|
| FiSMinessSize=8B, Base Model=Llama3-8B-Instruct2025.04 | 3.9 | 3.7 | 3.8 | 3.7 | 3.9 | 4.1 | 3.9 | |
| FiSMiness-agentSize=8B, Base Model=Llama3-8B-Instruct2025.04 | 3.8 | 3.7 | 3.6 | 3.4 | 3.7 | 3.5 | 3.5 | |
| FiSMiness-mtSize=8B, Base Model=Llama3-8B-Instruct2025.04 | 3.8 | 3.6 | 3.4 | 3.7 | 3.8 | 3.7 | 3.7 | |
| Llama3-8B-Instruct + Emotional-CoT+SFTSize=8B2025.04 | 3.7 | 3.6 | 3.2 | 3.7 | 3.6 | 3.4 | 3.4 | |
| GPT-4oSize=larger2025.04 | 3.6 | 3.8 | 3.7 | 3.6 | 3.6 | 3.2 | 3.5 | |
| original datasetSize=-2025.04 | 3.5 | 3.6 | 3.4 | 3.1 | 3.5 | 3.2 | 3.3 | |
| GPT-4Size=larger2025.04 | 3.5 | 3.7 | 3.4 | 3.3 | 3.5 | 3.5 | 3.4 | |
| Llama3-8B-Instruct + vanilla-SFTSize=8B2025.04 | 3.2 | 3.4 | 2.7 | 2.7 | 2.9 | 3.3 | 2.9 | |
| Llama3-70B-InstructSize=larger2025.04 | 3.1 | 3.3 | 2.7 | 3 | 3.2 | 3.1 | 3 | |
| Llama3-8B-InstructSize=8B2025.04 | 2.9 | 3 | 2.6 | 2.4 | 2.7 | 2.7 | 2.6 |