Irony Detection on Irony
-3.57Delta 1Qwen2.5-14B
Evaluation results
| Method | Links | ||
|---|---|---|---|
| Qwen2.5-14Bscenario=updated dataset (ours)2025.11 | -3.57 | 0.93 | |
| Qwen2.5-14Bscenario=semantic dataset2025.11 | 1.46 | 2.76 | |
| Llama3-8Bscenario=updated dataset (ours)2025.11 | 2 | 1.89 | |
| Ministral-8Bscenario=updated dataset (ours)2025.11 | 2.54 | 0.58 | |
| Mistral-12Bscenario=updated dataset (ours)2025.11 | 2.92 | 3.4 | |
| Qwen2.5-7Bscenario=updated dataset (ours)2025.11 | 6.82 | 2.31 | |
| Yi1.5-9Bscenario=updated dataset (ours)2025.11 | 7.59 | 0.55 | |
| Mistral-12Bscenario=semantic dataset2025.11 | 8.46 | 4.27 | |
| Llama3-8Bscenario=semantic dataset2025.11 | 9.66 | 3.05 | |
| Qwen2.5-7Bscenario=semantic dataset2025.11 | 10.37 | 2.77 | |
| Ministral-8Bscenario=semantic dataset2025.11 | 10.53 | 1.98 | |
| Yi1.5-9Bscenario=semantic dataset2025.11 | 12.86 | 2.31 | |
| Yi1.5-6Bscenario=updated dataset (ours)2025.11 | 16.35 | 0.75 | |
| Llama2-13Bscenario=updated dataset (ours)2025.11 | 18.23 | 1.12 | |
| Qwen2.5-7Bscenario=original dataset2025.11 | 19.77 | 4.86 | |
| Yi1.5-6Bscenario=semantic dataset2025.11 | 20.47 | 2.62 | |
| Llama2-13Bscenario=semantic dataset2025.11 | 23.15 | 2.42 | |
| Qwen2.5-14Bscenario=original dataset2025.11 | 27.75 | 9.78 | |
| Llama3-8Bscenario=original dataset2025.11 | 30.09 | 7.07 | |
| Ministral-8Bscenario=original dataset2025.11 | 39.66 | 7.58 | |
| Yi1.5-6Bscenario=original dataset2025.11 | 39.78 | 8.45 | |
| Mistral-12Bscenario=original dataset2025.11 | 40.43 | 10.59 | |
| Yi1.5-9Bscenario=original dataset2025.11 | 44.34 | 14.13 | |
| Llama2-13Bscenario=original dataset2025.11 | 52.46 | 7.97 |