Explanation Generation on ICEWS05-15 (test)
45.98BLEU-4GETER
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| GETERbackbone=Llama3-8B-Instruct2025.05 | 45.98 | 57.27 | 58.16 | 86.39 | |
| GETERbackbone=Mistral-7B-Instruct2025.05 | 45.07 | 56.48 | 57.7 | 86.13 | |
| GETERbackbone=Qwen2.5-7B-Instruct2025.05 | 44.72 | 56.17 | 57.22 | 86.01 | |
| Qwen2.5-7B-Instructtraining_protocol=LoRA, reasoning_chains=true2025.05 | 43.55 | 55.01 | 56.22 | 85.62 | |
| Mistral-7B-Instructtraining_protocol=LoRA, reasoning_chains=true2025.05 | 43.03 | 54.56 | 55.94 | 85.47 | |
| Llama3-8B-Instructtraining_protocol=LoRA, reasoning_chains=true2025.05 | 42.98 | 54.5 | 56.65 | 85.45 | |
| Qwen2.5-7B-Instructtraining_protocol=LoRA, reasoning_chains=false2025.05 | 28.6 | 40.52 | 45.76 | 80.39 | |
| Mistral-7B-Instructtraining_protocol=LoRA, reasoning_chains=false2025.05 | 28.26 | 40.13 | 45.96 | 80.45 | |
| Llama3-8B-Instructtraining_protocol=LoRA, reasoning_chains=false2025.05 | 27.59 | 39.63 | 45.8 | 80.17 | |
| GPT-4otraining_protocol=zero-shot, reasoning_chains=true2025.05 | 22.64 | 40.83 | 36.27 | 79.16 | |
| GPT-4otraining_protocol=zero-shot, reasoning_chains=false2025.05 | 10.74 | 23.63 | 30.94 | 68 | |
| Qwen2.5-7B-Instructtraining_protocol=zero-shot, reasoning_chains=true2025.05 | 10.53 | 28.53 | 26.32 | 72.04 | |
| Llama3-8B-Instructtraining_protocol=zero-shot, reasoning_chains=true2025.05 | 10.08 | 31.13 | 27.44 | 70.02 | |
| Mistral-7B-Instructtraining_protocol=zero-shot, reasoning_chains=true2025.05 | 7.95 | 27.4 | 23.6 | 70.73 | |
| Qwen2.5-7B-Instructtraining_protocol=zero-shot, reasoning_chains=false2025.05 | 7.81 | 19.87 | 30.27 | 65.94 | |
| Mistral-7B-Instructtraining_protocol=zero-shot, reasoning_chains=false2025.05 | 7.24 | 19.29 | 23.26 | 65.1 | |
| Llama3-8B-Instructtraining_protocol=zero-shot, reasoning_chains=false2025.05 | 2.27 | 12.88 | 10.53 | 58.28 |