Multi-label Toxin Prediction on Hospital Poly-intoxication Dataset
63.71F1 MicroDeToxR
Evaluation Results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| DeToxRCategory=Finetuned models2026.03 | 63.71 | 59.92 | 63.89 | 60.18 | 63.53 | 66.93 | |
| Qwen3 4B Instruct + SFTCategory=Finetuned models2026.03 | 58.89 | 55.31 | 52.33 | 52.11 | 67.33 | 68.42 | |
| XGBoostCategory=Baselines2026.03 | 57.12 | 35.36 | 50.07 | 30.85 | 66.48 | 45.21 | |
| MLPCategory=Baselines2026.03 | 54.39 | 31.98 | 45.42 | 26.72 | 67.79 | 50.32 | |
| Qwen3 4B InstructCategory=Base LLM inference, Zero-shot=true2026.03 | 52.63 | 50.82 | 45.84 | 56 | 61.79 | 57.79 | |
| MedGemma 4B ITCategory=Base LLM inference, Zero-shot=true2026.03 | 50.61 | 52.36 | 43.86 | 54.56 | 59.81 | 60.02 | |
| Qwen3 30B Instruct (MoE)Category=Base LLM inference, Zero-shot=true2026.03 | 50.14 | 47.26 | 50.21 | 60.74 | 50.07 | 49.56 | |
| Llama 3.1 8B InstructCategory=Base LLM inference, Zero-shot=true2026.03 | 49.7 | 48.94 | 50.07 | 59.58 | 49.51 | 50.02 | |
| History baselineCategory=Baselines2026.03 | 48.81 | 53.54 | 36.11 | 48.72 | 75.29 | 73.43 | |
| GPT OSS 20BCategory=Base LLM inference, Zero-shot=true2026.03 | 48.76 | 47.62 | 38.93 | 48.37 | 65.25 | 59.93 | |
| Qwen3 4B ThinkingCategory=Base LLM inference, Zero-shot=true2026.03 | 48.22 | 46.23 | 38.22 | 49.43 | 65.3 | 59.78 |