DOI QR코드

DOI QR Code

How to Optimize Prompting for Large Language Models in Clinical Research

  • Jeong Hyun Lee (Department of Radiology and Center for Imaging Science, Samsung Medical Center, Sungkyunkwan University School of Medicine) ;
  • Jaeseung Shin (Department of Radiology and Center for Imaging Science, Samsung Medical Center, Sungkyunkwan University School of Medicine)
  • Received : 2024.07.19
  • Accepted : 2024.08.05
  • Published : 2024.10.01

Abstract

Keywords

References

  1. Park SH, Suh CH. Reporting guidelines for artificial intelligence studies in healthcare (for both conventional and large language models): what's new in 2024. Korean J Radiol 2024;25:687-690
  2. Gu K, Lee JH, Shin J, Hwang JA, Min JH, Jeong WK, et al. Using GPT-4 for LI-RADS feature extraction and categorization with multilingual free-text reports. Liver Int 2024;44:1578-1587
  3. Schulhoff S, Ilie M, Balepur N, Kahadze K, Liu A, Si C, et al. The prompt report: a systematic survey of prompting techniques. arXiv [Preprint]. 2024 [accessed on July 14, 2024]. Available at: https://doi.org/10.48550/arXiv.2406.06608
  4. Kaddour J, Harris J, Mozes M, Bradley H, Raileanu R, McHardy R. Challenges and applications of large language models. arXiv [Preprint]. 2023 [accessed on July 14, 2024]. Available at: https://doi.org/10.48550/arXiv.2307.10169
  5. Khattab O, Singhvi A, Maheshwari P, Zhang Z, Santhanam K, Vardhamanan S, et al. DSPy: compiling declarative language model calls into self-improving pipelines. arXiv [Preprint]. 2023 [accessed on July 14, 2024]. Available at: https://doi.org/10.48550/arXiv.2310.03714
  6. Wang B, Yue X, Su Y, Sun H. Grokked transformers are implicit reasoners: a mechanistic journey to the edge of generalization. arXiv [Preprint]. 2024 [accessed on July 14, 2024]. Available at: https://doi.org/10.48550/arXiv.2405.15071
  7. Holtzman A, Buys J, Du L, Forbes M, Choi Y. The curious case of neural text degeneration. arXiv [Preprint]. 2019 [accessed on July 14, 2024]. Available at: https://doi.org/10.48550/arXiv.1904.09751
  8. Bhayana R. Chatbots and large language models in radiology: a practical primer for clinical and research applications. Radiology 2024;310:e232756
  9. Anthropic. Create a text completion [accessed on July 14, 2024]. Available at: https://docs.anthropic.com/en/api/complete
  10. OpenAI. Reproducible outputs [accessed on July 14, 2024]. Available at: https://platform.openai.com/docs/guides/textgeneration/reproducible-outputs
  11. Hugging Face. Text generation strategies [accessed on July 14, 2024]. Available at: https://huggingface.co/docs/transformers/main/en/generation_strategies#greedy-search
  12. Taori R, Gulrajani I, Zhang T, Dubois Y, Li X, Guestrin C, et al. Alpaca: a strong, replicable instruction-following model [accessed on July 14, 2024]. Available at: https://crfm.stanford.edu/2023/03/13/alpaca.html
  13. Abdin M, Jacobs SA, Awan AA, Aneja J, Awadallah A, Awadalla H, et al. Phi-3 technical report: a highly capable language model locally on your phone. arXiv [Preprint]. 2024 [accessed on July 14, 2024]. Available at: https://doi.org/10.48550/arXiv.2404.14219