零样本因果图外推：基于大语言模型从文本中提取
Zero-shot Causal Graph Extrapolation from Text via LLMs
AI总结：
本研究评估了大语言模型在零样本条件下从文本推断因果关系的能力，并通过迭代成对查询外推因果图，在生物医学摘要基准上验证了其有效性与应用潜力。
摘要：
我们评估了大语言模型（LLMs）从自然语言中推断因果关系的能力。与传统的自然语言处理和深度学习技术相比，LLMs 在无需（显式）训练样本的情况下，在成对关系基准测试中表现出具有竞争力的性能。这促使我们将方法扩展到通过迭代成对查询来外推因果图。我们在一个由专家验证的、具有真实因果图的生物医学摘要基准上进行了初步分析。结果令人鼓舞，支持采用 LLMs 进行因果推断中这一关键步骤，尤其是在医学领域，因为待分析的科学文本量可能巨大，且因果陈述往往是隐含的。
英文摘要：
We evaluate the ability of large language models (LLMs) to infer causal relations from natural language. Compared to traditional natural language processing and deep learning techniques, LLMs show competitive performance in a benchmark of pairwise relations without needing (explicit) training samples. This motivates us to extend our approach to extrapolating causal graphs through iterated pairwise queries. We perform a preliminary analysis on a benchmark of biomedical abstracts with ground-truth causal graphs validated by experts. The results are promising and support the adoption of LLMs for such a crucial step in causal inference, especially in medical domains, where the amount of scientific text to analyse might be huge, and the causal statements are often implicit.
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。
