Empathy evaluation on E-Dialogue
99.4Empathy ScoreAligner
Evaluation Results
| Method | Links | |
|---|---|---|
| AlignerAligner size=7B, Upstream LLM=Alpaca-7B, Zero-shot=true2024.02 | 99.4 | |
| AlignerAligner size=13B, Upstream LLM=Alpaca-7B, Zero-shot=true2024.02 | 99 | |
| AlignerAligner size=7B, Upstream LLM=Beaver-7B, Zero-shot=true2024.02 | 98.3 | |
| AlignerAligner size=13B, Upstream LLM=Beaver-7B, Zero-shot=true2024.02 | 98.1 | |
| AlignerAligner size=2B, Upstream LLM=Alpaca-7B, Zero-shot=true2024.02 | 97.7 | |
| AlignerAligner size=7B, Upstream LLM=Llama2-13B-Chat, Zero-shot=true2024.02 | 96.6 | |
| AlignerAligner size=13B, Upstream LLM=Vicuna-7B, Zero-shot=true2024.02 | 96.3 | |
| AlignerAligner size=13B, Upstream LLM=Llama2-7B-Chat, Zero-shot=true2024.02 | 96 | |
| AlignerAligner size=13B, Upstream LLM=Vicuna-13B, Zero-shot=true2024.02 | 95.9 | |
| AlignerAligner size=7B, Upstream LLM=Llama2-7B-Chat, Zero-shot=true2024.02 | 95.6 | |
| AlignerAligner size=7B, Upstream LLM=Vicuna-7B, Zero-shot=true2024.02 | 95.4 | |
| AlignerAligner size=13B, Upstream LLM=Llama2-13B-Chat, Zero-shot=true2024.02 | 95.4 | |
| AlignerAligner size=2B, Upstream LLM=Beaver-7B, Zero-shot=true2024.02 | 95.3 | |
| AlignerAligner size=7B, Upstream LLM=Llama2-70B-Chat, Zero-shot=true2024.02 | 95 | |
| AlignerAligner size=13B, Upstream LLM=Llama2-70B-Chat, Zero-shot=true2024.02 | 94.6 | |
| AlignerAligner size=7B, Upstream LLM=Vicuna-13B, Zero-shot=true2024.02 | 94 | |
| AlignerAligner size=13B, Upstream LLM=Claude 2, Zero-shot=true2024.02 | 90.6 | |
| AlignerAligner size=7B, Upstream LLM=Claude 2, Zero-shot=true2024.02 | 90.4 | |
| AlignerAligner size=13B, Upstream LLM=Vicuna-33B, Zero-shot=true2024.02 | 90 | |
| AlignerAligner size=7B, Upstream LLM=Vicuna-33B, Zero-shot=true2024.02 | 89.3 | |
| AlignerAligner size=2B, Upstream LLM=Llama2-7B-Chat, Zero-shot=true2024.02 | 88.1 | |
| AlignerAligner size=2B, Upstream LLM=Llama2-70B-Chat, Zero-shot=true2024.02 | 86.7 | |
| AlignerAligner size=2B, Upstream LLM=Llama2-13B-Chat, Zero-shot=true2024.02 | 85.3 | |
| AlignerAligner size=2B, Upstream LLM=Claude 2, Zero-shot=true2024.02 | 83.1 | |
| AlignerAligner size=2B, Upstream LLM=Vicuna-13B, Zero-shot=true2024.02 | 53.9 | |
| AlignerAligner size=2B, Upstream LLM=Vicuna-33B, Zero-shot=true2024.02 | 45.7 | |
| AlignerAligner size=2B, Upstream LLM=Vicuna-7B, Zero-shot=true2024.02 | 44.9 | |
| AlignerAligner size=13B, Upstream LLM=GPT-3.5, Zero-shot=true2024.02 | 43.7 | |
| AlignerAligner size=13B, Upstream LLM=GPT-4, Zero-shot=true2024.02 | 42.6 | |
| AlignerAligner size=7B, Upstream LLM=GPT-4, Zero-shot=true2024.02 | 27.7 | |
| AlignerAligner size=2B, Upstream LLM=GPT-3.5, Zero-shot=true2024.02 | 26.3 | |
| AlignerAligner size=2B, Upstream LLM=GPT-4, Zero-shot=true2024.02 | 26 | |
| AlignerAligner size=7B, Upstream LLM=GPT-3.5, Zero-shot=true2024.02 | 25.6 |