MedConceptsQA: Open Source Medical Concepts QA Benchmark
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866929343215697920 |
|---|---|
| author | Shoham, Ofir Ben Rappoport, Nadav |
| author_facet | Shoham, Ofir Ben Rappoport, Nadav |
| contents | We present MedConceptsQA, a dedicated open source benchmark for medical concepts question answering. The benchmark comprises of questions of various medical concepts across different vocabularies: diagnoses, procedures, and drugs. The questions are categorized into three levels of difficulty: easy, medium, and hard. We conducted evaluations of the benchmark using various Large Language Models. Our findings show that pre-trained clinical Large Language Models achieved accuracy levels close to random guessing on this benchmark, despite being pre-trained on medical data. However, GPT-4 achieves an absolute average improvement of nearly 27%-37% (27% for zero-shot learning and 37% for few-shot learning) when compared to clinical Large Language Models. Our benchmark serves as a valuable resource for evaluating the understanding and reasoning of medical concepts by Large Language Models. Our benchmark is available at https://huggingface.co/datasets/ofir408/MedConceptsQA |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_07348 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | MedConceptsQA: Open Source Medical Concepts QA Benchmark Shoham, Ofir Ben Rappoport, Nadav Computation and Language Machine Learning We present MedConceptsQA, a dedicated open source benchmark for medical concepts question answering. The benchmark comprises of questions of various medical concepts across different vocabularies: diagnoses, procedures, and drugs. The questions are categorized into three levels of difficulty: easy, medium, and hard. We conducted evaluations of the benchmark using various Large Language Models. Our findings show that pre-trained clinical Large Language Models achieved accuracy levels close to random guessing on this benchmark, despite being pre-trained on medical data. However, GPT-4 achieves an absolute average improvement of nearly 27%-37% (27% for zero-shot learning and 37% for few-shot learning) when compared to clinical Large Language Models. Our benchmark serves as a valuable resource for evaluating the understanding and reasoning of medical concepts by Large Language Models. Our benchmark is available at https://huggingface.co/datasets/ofir408/MedConceptsQA |
| title | MedConceptsQA: Open Source Medical Concepts QA Benchmark |
| topic | Computation and Language Machine Learning |
| url | https://arxiv.org/abs/2405.07348 |