Reasoning evaluation on DialogSum
99.1ReasoningAligner
Evaluation Results
| Method | Links | |
|---|---|---|
| AlignerAligner size=13B, Upstream LLM=Llama2-7B-Chat, Zero-shot=true2024.02 | 99.1 | |
| AlignerAligner size=7B, Upstream LLM=Llama2-7B-Chat, Zero-shot=true2024.02 | 98.8 | |
| AlignerAligner size=13B, Upstream LLM=Beaver-7B, Zero-shot=true2024.02 | 87.6 | |
| AlignerAligner size=7B, Upstream LLM=Beaver-7B, Zero-shot=true2024.02 | 83.5 | |
| AlignerAligner size=13B, Upstream LLM=Alpaca-7B, Zero-shot=true2024.02 | 82.9 | |
| AlignerAligner size=7B, Upstream LLM=Alpaca-7B, Zero-shot=true2024.02 | 78.7 | |
| AlignerAligner size=13B, Upstream LLM=Vicuna-7B, Zero-shot=true2024.02 | 78.5 | |
| AlignerAligner size=7B, Upstream LLM=Vicuna-7B, Zero-shot=true2024.02 | 73.6 | |
| AlignerAligner size=13B, Upstream LLM=Llama2-13B-Chat, Zero-shot=true2024.02 | 73.1 | |
| AlignerAligner size=7B, Upstream LLM=Llama2-13B-Chat, Zero-shot=true2024.02 | 70.8 | |
| AlignerAligner size=7B, Upstream LLM=Llama2-70B-Chat, Zero-shot=true2024.02 | 70.1 | |
| AlignerAligner size=2B, Upstream LLM=Llama2-7B-Chat, Zero-shot=true2024.02 | 69.5 | |
| AlignerAligner size=13B, Upstream LLM=Llama2-70B-Chat, Zero-shot=true2024.02 | 69.2 | |
| AlignerAligner size=13B, Upstream LLM=Vicuna-33B, Zero-shot=true2024.02 | 65.9 | |
| AlignerAligner size=2B, Upstream LLM=Beaver-7B, Zero-shot=true2024.02 | 60.7 | |
| AlignerAligner size=13B, Upstream LLM=Vicuna-13B, Zero-shot=true2024.02 | 58.7 | |
| AlignerAligner size=2B, Upstream LLM=Alpaca-7B, Zero-shot=true2024.02 | 58.5 | |
| AlignerAligner size=2B, Upstream LLM=Vicuna-7B, Zero-shot=true2024.02 | 58.5 | |
| AlignerAligner size=7B, Upstream LLM=Vicuna-33B, Zero-shot=true2024.02 | 58.5 | |
| AlignerAligner size=2B, Upstream LLM=Llama2-13B-Chat, Zero-shot=true2024.02 | 53.4 | |
| AlignerAligner size=7B, Upstream LLM=Vicuna-13B, Zero-shot=true2024.02 | 49.5 | |
| AlignerAligner size=2B, Upstream LLM=Llama2-70B-Chat, Zero-shot=true2024.02 | 47.9 | |
| AlignerAligner size=2B, Upstream LLM=Vicuna-33B, Zero-shot=true2024.02 | 39.3 | |
| AlignerAligner size=2B, Upstream LLM=Vicuna-13B, Zero-shot=true2024.02 | 24 | |
| AlignerAligner size=13B, Upstream LLM=Claude 2, Zero-shot=true2024.02 | 17.2 | |
| AlignerAligner size=13B, Upstream LLM=GPT-3.5, Zero-shot=true2024.02 | 15.6 | |
| AlignerAligner size=7B, Upstream LLM=Claude 2, Zero-shot=true2024.02 | 10.4 | |
| AlignerAligner size=13B, Upstream LLM=GPT-4, Zero-shot=true2024.02 | 9.7 | |
| AlignerAligner size=7B, Upstream LLM=GPT-3.5, Zero-shot=true2024.02 | 6.8 | |
| AlignerAligner size=7B, Upstream LLM=GPT-4, Zero-shot=true2024.02 | 6.2 | |
| AlignerAligner size=2B, Upstream LLM=Claude 2, Zero-shot=true2024.02 | 6 | |
| AlignerAligner size=2B, Upstream LLM=GPT-3.5, Zero-shot=true2024.02 | 3.3 | |
| AlignerAligner size=2B, Upstream LLM=GPT-4, Zero-shot=true2024.02 | 2.3 |