Sarcasm Detection on MUStARD (held-out)
65.8F1 ScoreOMNISAPIENS-7B SFT
Evaluation Results
| Method | Links | |
|---|---|---|
| OMNISAPIENS-7B SFTfine-tuning epochs=1, training mode=SFT2025.10 | 65.8 | |
| Qwen 2.5-Omni-7Bfine-tuning epochs=0, training mode=pre-trained2025.10 | 65.6 | |
| OMNISAPIENS-7B RLzero-shot=true2025.10 | 59.6 | |
| Gemma-3-4Bfine-tuning epochs=0, training mode=pre-trained2025.10 | 52.9 | |
| Qwen-2.5-VL-7Bfine-tuning epochs=0, training mode=pre-trained2025.10 | 51.1 | |
| Qwen 2.5-Omni-7B SFTfine-tuning epochs=1, training mode=SFT2025.10 | 47.3 | |
| Qwen 2.5-Omni-7Bzero-shot=true2025.10 | 44.5 | |
| HumanOmniV2-7Bfine-tuning epochs=0, training mode=pre-trained2025.10 | 39.5 |