تقرير
Exploring the Boundaries of GPT-4 in Radiology
| العنوان: | Exploring the Boundaries of GPT-4 in Radiology |
|---|---|
| المؤلفون: | Liu, Qianchu, Hyland, Stephanie, Bannur, Shruthi, Bouzid, Kenza, Castro, Daniel C., Wetscherek, Maria Teodora, Tinn, Robert, Sharma, Harshita, Pérez-García, Fernando, Schwaighofer, Anton, Rajpurkar, Pranav, Khanna, Sameer Tajdin, Poon, Hoifung, Usuyama, Naoto, Thieme, Anja, Nori, Aditya V., Lungren, Matthew P., Oktay, Ozan, Alvarez-Valle, Javier |
| سنة النشر: | 2023 |
| المجموعة: | Computer Science |
| مصطلحات موضوعية: | Computer Science - Computation and Language |
| الوصف: | The recent success of general-domain large language models (LLMs) has significantly changed the natural language processing paradigm towards a unified foundation model across domains and applications. In this paper, we focus on assessing the performance of GPT-4, the most capable LLM so far, on the text-based applications for radiology reports, comparing against state-of-the-art (SOTA) radiology-specific models. Exploring various prompting strategies, we evaluated GPT-4 on a diverse range of common radiology tasks and we found GPT-4 either outperforms or is on par with current SOTA radiology models. With zero-shot prompting, GPT-4 already obtains substantial gains ($\approx$ 10% absolute improvement) over radiology models in temporal sentence similarity classification (accuracy) and natural language inference ($F_1$). For tasks that require learning dataset-specific style or schema (e.g. findings summarisation), GPT-4 improves with example-based prompting and matches supervised SOTA. Our extensive error analysis with a board-certified radiologist shows GPT-4 has a sufficient level of radiology knowledge with only occasional errors in complex context that require nuanced domain knowledge. For findings summarisation, GPT-4 outputs are found to be overall comparable with existing manually-written impressions. Comment: EMNLP 2023 main |
| نوع الوثيقة: | Working Paper |
| URL الوصول: | http://arxiv.org/abs/2310.14573 |
| رقم الأكسشن: | edsarx.2310.14573 |
| قاعدة البيانات: | arXiv |
| الوصف غير متاح. |