大型语言模型能否构建因果图？
Can large language models build causal graphs?
AI总结：
本文评估大型语言模型能否通过自动评分因果图中的边来辅助因果图构建，从而减轻人工查阅文献和专家讨论的负担。
摘要：
构建因果图可能是一个费力的过程。为了确保所有相关的因果路径都被捕获，研究人员通常需要与临床医生和专家讨论，同时还要查阅大量相关医学文献。通过编码常识和医学知识，大型语言模型（LLMs）提供了一个机会，可以通过自动对潜在图中的边（即两个变量之间的连接）进行评分来简化这一过程。然而，已有研究表明，LLMs 对用户使用的探测词、上下文和提示词的选择较为脆弱。在这项工作中，我们评估了 LLMs 是否可以作为补充因果图开发的有用工具。
英文摘要：
Building causal graphs can be a laborious process. To ensure all relevant causal pathways have been captured, researchers often have to discuss with clinicians and experts while also reviewing extensive relevant medical literature. By encoding common and medical knowledge, large language models (LLMs) represent an opportunity to ease this process by automatically scoring edges (i.e., connections between two variables) in potential graphs. LLMs however have been shown to be brittle to the choice of probing words, context, and prompts that the user employs. In this work, we evaluate if LLMs can be a useful tool in complementing causal graph development.
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。
