Report Generation on MIMIC IV
35.06METEORGEM
Evaluation Results
| Method | Links | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| GEM2026.02 | 35.06 | 44.65 | 50.81 | 11.6 | 23.81 | 87.78 | — | — | — | — | |
| Gemini 2.5Retrieval Configuration=Our Framework2026.02 | 33.4 | — | — | — | — | 86.2 | 4.2 | 41.9 | 15.5 | 30 | |
| GPT-4.1-miniRetrieval Configuration=Our Framework2026.02 | 32.1 | — | — | — | — | 85.1 | 3.5 | 38 | 12.4 | 29.1 | |
| Gemini 2.5Retrieval Configuration=with RAG2026.02 | 31.6 | — | — | — | — | 83.3 | 2 | 36.8 | 9.9 | 21.4 | |
| GPT-4.1-miniRetrieval Configuration=with RAG2026.02 | 29.1 | — | — | — | — | 83.1 | 1.9 | 35.1 | 8.1 | 22.1 | |
| Gemini 2.5Retrieval Configuration=Baselines without Retrieval2026.02 | 28.9 | — | — | — | — | 82.9 | 1.4 | 29.5 | 7 | 14.7 | |
| DeepSeek-ChatRetrieval Configuration=Our Framework2026.02 | 28.7 | — | — | — | — | 83.9 | 2.9 | 34 | 9.7 | 20.3 | |
| GPT-4.1-miniRetrieval Configuration=Baselines without Retrieval2026.02 | 28.2 | — | — | — | — | 82.5 | 1.2 | 30.1 | 6.4 | 14.4 | |
| DeepSeek-ChatRetrieval Configuration=with RAG2026.02 | 27.2 | — | — | — | — | 79.9 | 1.5 | 22.9 | 5.7 | 15.7 | |
| DeepSeek-ChatRetrieval Configuration=Baselines without Retrieval2026.02 | 25.1 | — | — | — | — | 80.9 | 0.6 | 20.5 | 4.2 | 12 | |
| PULSE2026.02 | 20.74 | 40.43 | 6.09 | 0.93 | 8.02 | 83.37 | — | — | — | — | |
| CAMEL2026.02 | 17.57 | 62.59 | 23.11 | 3.3 | 15.56 | 82.1 | — | — | — | — |