从大模型中提取潜在因果假设，生成可解释的因果图谱。
Causality Elicitation from Large Language Models
- 通过生成文本并提取事件，构建统一事件列表。
- 用二值向量表示文档事件分布，发现候选因果关系。
- 适合想理解模型隐含逻辑的研究者和决策分析场景。
大型语言模型（LLMs）在海量数据上训练，其参数中编码了大量知识。本文提出一个流程，用于从LLMs中提取因果关系：首先对特定主题生成大量文档；其次从每篇文档中提取事件列表；然后将跨文档出现的事件归类为标准事件；接着为每篇文档构建基于标准事件的二值指示向量；最后使用因果发现方法估计候选因果图。该方法不保证反映真实世界因果，而是提供一个可检查的框架，展示模型可能持有的因果假设集合，包括变量与候选图结构。
原文摘要 · Abstract (English)
Large language models (LLMs) are trained on enormous amounts of data and encode knowledge in their parameters. We propose a pipeline to elicit causal relationships from LLMs. Specifically, (i) we sample many documents from LLMs on a given topic, (ii) we extract an event list from from each document, (iii) we group events that appear across documents into canonical events, (iv) we construct a binary indicator vector for each document over canonical events, and (v) we estimate candidate causal graphs using causal discovery methods. Our approach does not guarantee real-world causality. Rather, it provides a framework for presenting the set of causal hypotheses that LLMs can plausibly assume, as an inspectable set of variables and candidate graphs.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。