Clinical Summarization on SOAP Summary (Factuality & Quality Metrics)
2.08HallucinationAgenticSum
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| AgenticSum2026.02 | 2.08 | 3.33 | 4.23 | 3.99 | |
| MedAlpaca-7B2026.02 | 2.13 | 3.07 | 4.68 | 3.86 | |
| ConTextual2026.02 | 2.15 | 3.28 | 4.5 | 4.67 | |
| Llama-3.2-3B2026.02 | 2.2 | 3.14 | 4.38 | 3.84 | |
| Mistral-7B2026.02 | 2.23 | 2.99 | 4.05 | 3.74 | |
| BioBART2026.02 | 2.38 | 2.87 | 4.15 | 3.72 | |
| Flan-T52026.02 | 2.41 | 3.12 | 4.52 | 3.75 | |
| Gemma3-1B2026.02 | 2.42 | 2.98 | 4.22 | 3.68 | |
| T5-Large2026.02 | 2.47 | 2.82 | 4.02 | 3.65 |