Improving Generalizability of Extracting Social Determinants of Health Using Large Language Models through Prompt-tuning

arXiv:2403.12374v1 Announce Type: new
Abstract: The progress in natural language processing (NLP) using large language models (LLMs) has greatly improved patient information extraction from clinical narratives. However, most methods based on the fine-tuning strategy have limited transfer learning ability for cross-domain applications. This study proposed a novel approach that employs a soft prompt-based learning architecture, which introduces trainable prompts to guide LLMs toward desired outputs. We examined two types of LLM architectures, including encoder-only GatorTron and decoder-only GatorTronGPT, and evaluated …

abstract applications arxiv clinical cs.cl domain extraction fine-tuning health however information information extraction language language models language processing large language large language models llms natural natural language natural language processing nlp patient processing progress prompt social strategy study through transfer transfer learning type