Back

Comparison of Prompt Engineering and Fine-Tuning Strategies in Large Language Models in the Classification of Clinical Notes

Zhang, X.; Talukdar, N.; Vemulapalli, S.; Ahn, S.; Wang, J.; Meng, H.; Murtaza, S. M. B.; Leshchiner, D.; Dave, A. A.; Joseph, D. F.; Witteveen-Lane, M.; Chesla, D.; Zhou, J.; Chen, B.

2024-02-08 health informatics
10.1101/2024.02.07.24302444 medRxiv
Show abstract

The emerging large language models (LLMs) are actively evaluated in various fields including healthcare. Most studies have focused on established benchmarks and standard parameters; however, the variation and impact of prompt engineering and fine-tuning strategies have not been fully explored. This study benchmarks GPT-3.5 Turbo, GPT-4, and Llama-7B against BERT models and medical fellows annotations in identifying patients with metastatic cancer from discharge summaries. Results revealed that clear, concise prompts incorporating reasoning steps significantly enhanced performance. GPT-4 exhibited superior performance among all models. Notably, one-shot learning and fine-tuning provided no incremental benefit. The models accuracy sustained even when keywords for metastatic cancer were removed or when half of the input tokens were randomly discarded. These findings underscore GPT-4s potential to substitute specialized models, such as PubMedBERT, through strategic prompt engineering, and suggest opportunities to improve open-source models, which are better suited to use in clinical settings.

Matching journals

The top 6 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.