In this work, we propose a novel method for Bayesian Networks (BNs) structure elicitation that is based on the initialization of several LLMs with different experiences, independently querying them to create a structure of the BN, and further obtaining the final structure by majority voting. We compare the method with one alternative method on various widely and not widely known BNs of different sizes and study the scalability of both methods on them. We also propose an approach to check the contamination of BNs in LLM, which shows that some widely known BNs are inapplicable for testing the LLM usage for BNs structure elicitation. We also show that some BNs may be inapplicable for such experiments because their node names are indistinguishable. The experiments on the other BNs show that our method performs better than the existing method with one of the three studied LLMs; however, the performance of both methods significantly decreases with the increase in BN size.

翻译：本文提出了一种新颖的贝叶斯网络结构提取方法。该方法通过初始化多个具有不同经验背景的大型语言模型，独立查询各模型以生成贝叶斯网络结构，并采用多数投票机制确定最终结构。我们将该方法与另一种替代方法在多种不同规模（包括广为人知及非广为人知）的贝叶斯网络上进行比较，并研究两种方法在这些网络上的可扩展性。同时，我们提出了一种检测大型语言模型中贝叶斯网络污染的方法，结果表明某些广为人知的贝叶斯网络不适用于测试大型语言模型在贝叶斯网络结构提取中的应用。研究还发现，部分贝叶斯网络因其节点名称难以区分而不适用于此类实验。在其他贝叶斯网络上的实验表明，在三种测试的大型语言模型中，我们的方法在其中一个模型上的表现优于现有方法；然而，随着贝叶斯网络规模的增大，两种方法的性能均显著下降。