Scan-level report labelling on Cancer (test)
100Balanced AccuracyDirect Query
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| Direct QueryQuery Model=GPT-42024.10 | 100 | — | — | 100 | |
| Summary-QuerySummary Model=Llama3, Query Model=Llama32024.10 | 100 | 0 | 1 | 100 | |
| Summary-QuerySummary Model=Z-SFT, Query Model=Zephyr2024.10 | 99.4 | 0 | 1 | 99.3 | |
| Direct QueryQuery Model=Zephyr2024.10 | 99.3 | 0 | 1 | 99.2 | |
| Summary-QuerySummary Model=Zephyr, Query Model=Zephyr2024.10 | 98.5 | 0 | 1 | 98.5 | |
| Direct QueryQuery Model=Llama32024.10 | 97.8 | 0.014 | 0.999 | 97.7 |