使用大语言模型（LLMs）从医学文本中提取因果关系
Causality extraction from medical text using Large Language Models (LLMs)
AI总结：
本研究探索大语言模型等从妊娠糖尿病临床实践指南提取因果关系的效果，实验发现BioBERT以0.72的平均F1得分表现最优，还发布了相关代码和标注语料库。
摘要：
本研究探讨了包括大语言模型在内的自然语言模型从医学文本，特别是临床实践指南（CPGs）中提取因果关系的潜力。研究展示了从妊娠糖尿病临床实践指南中提取因果关系的结果，这是该领域的首次尝试。我们报告了一组使用BERT变体（BioBERT、DistilBERT和BERT）以及大语言模型（LLMs）即GPT-4和LLAMA2的实验。实验表明，BioBERT的表现优于包括大语言模型在内的其他模型，平均F1得分为0.72。GPT-4和LLAMA2的结果表现相近，但一致性较差。我们还发布了相关代码以及一份在妊娠糖尿病临床实践指南中标注了因果陈述的语料库。
英文摘要：
This study explores the potential of natural language models, including large language models, to extract causal relations from medical texts, specifically from Clinical Practice Guidelines (CPGs). The outcomes causality extraction from Clinical Practice Guidelines for gestational diabetes are presented, marking a first in the field. We report on a set of experiments using variants of BERT (BioBERT, DistilBERT, and BERT) and using Large Language Models (LLMs), namely GPT-4 and LLAMA2. Our experiments show that BioBERT performed better than other models, including the Large Language Models, with an average F1-score of 0.72. GPT-4 and LLAMA2 results show similar performance but less consistency. We also release the code and an annotated a corpus of causal statements within the Clinical Practice Guidelines for gestational diabetes.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
