Bargaining on AmazonHistoryPrice CI 1.0 (test)
44CountGPT-4
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| GPT-4Role=Buyer2024.02 | 44 | 6.82 | -10.35 | |
| GPT-4Role=Seller2024.02 | 44 | 40.91 | 25.02 | |
| ChatGPTRole=Buyer2024.02 | 42 | 19.05 | -6.8 | |
| ChatGPTRole=Seller2024.02 | 42 | 19.05 | -1.2 | |
| Qwen-7B-ChatRole=Seller2024.02 | 41 | 36.59 | -21.77 | |
| Yi-34B-ChatRole=Seller2024.02 | 40 | 62.5 | -11.56 | |
| Llama-2-70b-chatRole=Seller2024.02 | 40 | 77.5 | -36.65 | |
| Baichuan2-13B-ChatRole=Seller2024.02 | 40 | 65 | -47.29 | |
| Yi-34B-ChatRole=Buyer2024.02 | 39 | 12.82 | -18.56 | |
| Mistral-7B-InstructRole=Seller2024.02 | 39 | 92.31 | -42.95 | |
| Mistral-7B-InstructRole=Buyer2024.02 | 38 | 42.11 | -11.85 | |
| Llama-2-13b-chatRole=Buyer2024.02 | 38 | 34.21 | -35.43 | |
| Llama-2-7b-chatRole=Buyer2024.02 | 36 | 25 | -8.99 | |
| Qwen-14B-ChatRole=Seller2024.02 | 36 | 63.89 | -28.08 | |
| Llama-2-70b-chatRole=Buyer2024.02 | 35 | 34.29 | -25.33 | |
| Llama-2-13b-chatRole=Seller2024.02 | 34 | 73.53 | -26.32 | |
| Baichuan2-7B-ChatRole=Seller2024.02 | 34 | 79.41 | -115.31 | |
| Qwen-14B-ChatRole=Buyer2024.02 | 33 | 27.27 | -37.96 | |
| Qwen-7B-ChatRole=Buyer2024.02 | 32 | 34.38 | -61.04 | |
| Mixtral-8x7B-InstructRole=Buyer2024.02 | 30 | 16.67 | -3.53 | |
| ChatGLM3-6BRole=Buyer2024.02 | 30 | 26.67 | -42.66 | |
| Baichuan2-7B-ChatRole=Buyer2024.02 | 30 | 36.67 | -36.57 | |
| Yi-6B-ChatRole=Buyer2024.02 | 29 | 17.24 | -6.78 | |
| Baichuan2-13B-ChatRole=Buyer2024.02 | 26 | 23.08 | 21.17 | |
| Mixtral-8x7B-InstructRole=Seller2024.02 | 26 | 65.38 | -12.83 | |
| ChatGLM3-6BRole=Seller2024.02 | 26 | 69.23 | -69.84 | |
| Llama-2-7b-chatRole=Seller2024.02 | 25 | 52 | -22.28 | |
| Yi-6B-ChatRole=Seller2024.02 | 4 | 100 | -17.15 |