Causal structure discovery from observations can be improved by integrating background knowledge provided by an expert to reduce the hypothesis space. Recently, Large Language Models (LLMs) have begun to be considered as sources of prior information given the low cost of querying them relative to a human expert. In this work, firstly, we propose a set of metrics for assessing LLM judgments for causal graph discovery independently of the downstream algorithm. Secondly, we systematically study a set of prompting designs that allows the model to specify priors about the structure of the causal graph. Finally, we present a general methodology for the integration of LLM priors in graph discovery algorithms, finding that they help improve performance on common-sense benchmarks and especially when used for assessing edge directionality. Our work highlights the potential as well as the shortcomings of the use of LLMs in this problem space.

整合专家提供的背景知识可以改善观测数据的因果结构发现，并且由于对比人工专家而言查询它们的成本较低，最近开始将大型语言模型（LLM）视为提供先验信息的来源。本研究首先提出了一组用于独立于下游算法评估LLM判断因果图发现的度量标准。其次，我们系统地研究了一组提示设计，使模型能够指定关于因果图结构的先验。最后，我们提出了一种将LLM先验整合到图发现算法中的通用方法，发现它们在常识基准和特别是用于评估边缘方向性时有助于提高性能。我们的研究突显了在该问题空间中使用LLM的潜力和局限性。

大型语言模型对因果图发现的有效先验