Note-table consistency verification on EHRCon Nursing notes
72.53RecallEHR-INSPECTOR
Evaluation Results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| EHR-INSPECTORBase LLM=Gemini 2.5 Flash, Evaluation Setting=Lenient2026.05 | 72.53 | — | — | — | — | 71.59 | |
| EHR-INSPECTORBase LLM=Gemini 2.5 Flash, Evaluation Setting=Harsh2026.05 | 65.26 | — | — | — | — | 62.59 | |
| EHR-INSPECTORBase LLM=Qwen3 32B, Evaluation Setting=Lenient2026.05 | 60.36 | — | — | — | — | 62.88 | |
| EHR-INSPECTORBase LLM=Qwen3 32B, Evaluation Setting=Harsh2026.05 | 51.58 | — | — | — | — | 52.69 | |
| EHR-INSPECTORBase LLM=MedGemma 27B, Evaluation Setting=Lenient2026.05 | 50.31 | — | — | — | — | 47.46 | |
| EHR-INSPECTORBase LLM=MedGemma 27B, Evaluation Setting=Harsh2026.05 | 45.57 | — | — | — | — | 41.5 | |
| CheckEHRBase LLM=Gemini 2.5 Flash, Evaluation Setting=Lenient2026.05 | 38.07 | — | — | — | — | 64.48 | |
| CheckEHRBase LLM=Gemini 2.5 Flash, Evaluation Setting=Harsh2026.05 | 35.16 | — | — | — | — | 55.59 | |
| EHR-INSPECTORBase LLM=GPT-OSS 20B, Evaluation Setting=Lenient2026.05 | 28.38 | — | — | — | — | 61.4 | |
| EHR-INSPECTORBase LLM=GPT-OSS 20B, Evaluation Setting=Harsh2026.05 | 24.49 | — | — | — | — | 51.77 | |
| CheckEHRBase LLM=Qwen3 32B, Evaluation Setting=Lenient2026.05 | 24.05 | — | — | — | — | 58.1 | |
| CheckEHRBase LLM=GPT-OSS 20B, Evaluation Setting=Lenient2026.05 | 24 | — | — | — | — | 55.85 | |
| CheckEHRBase LLM=GPT-OSS 20B, Evaluation Setting=Harsh2026.05 | 22.2 | — | — | — | — | 47.2 | |
| CheckEHRBase LLM=Qwen3 32B, Evaluation Setting=Harsh2026.05 | 22.12 | — | — | — | — | 52.14 | |
| CheckEHRBase LLM=MedGemma 27B, Evaluation Setting=Lenient2026.05 | 5.56 | — | — | — | — | 32.54 | |
| CheckEHRBase LLM=MedGemma 27B, Evaluation Setting=Harsh2026.05 | 4.8 | — | — | — | — | 26.09 | |
| CheckEHR2026.05 | — | 73.64 | 54.86 | 64.87 | 48.4 | — | |
| EHR-INSPECTOR2026.05 | — | 77.42 | 89.85 | 67.39 | 76.38 | — |