基于相互兼容性评估双变量因果陈述
Evaluating Bivariate Causal Statements Based on Mutual Compatibility
AI总结：
针对一组变量上的双变量因果陈述，提出基于兼容性分数的评估方法，通过量化因果模型引入的额外混杂程度或全局一致性约束来区分正确与错误的因果陈述，并应用于大语言模型生成的因果主张。
摘要：
对于许多现实世界系统，因果真相难以获得，使得关于因果效应的主张难以评估。我们开发了评估一组 $n$ 个变量上 $inom{n}{2}$ 个双变量因果陈述集合的方法。在线性无环陈述的设定下，任何这样的集合都可以扩展为唯一的多元因果模型，但我们认为如果该诱导模型为了解释观测相关性而施加了实质性的额外混杂，则其不可信。我们引入了一个兼容性分数来量化这种可信度概念，特别是不依赖于忠实性假设。此外，我们基于从无环性和忠实性假设导出的全局一致性约束，为纯图的双变量因果陈述定义了一个不兼容性分数。我们提供了理论和经验证据，表明这两个分数在一般设置中能够成功区分正确和错误的因果陈述。此外，我们通过分析大语言模型做出的因果主张，展示了我们方法的实际适用性。我们的工作旨在为评估从人类专家或人工智能获得的因果信息的可靠性提供基础，特别是在无法获得其他形式验证的情况下。
英文摘要：
For many real-world systems, causal ground truth is difficult to obtain, making claims about causal effects hard to assess. We develop methods for evaluating collections of $\binom{n}{2}$ bivariate causal statements over a set of $n$ variables. In the setting of acyclic linear statements, any such collection can be extended to a unique multivariate causal model, but we argue that this induced model is implausible if it imposes substantial additional confounding to explain observed correlations. We introduce a compatibility score that quantifies this notion of plausibility, notably without relying on the faithfulness assumption. Additionally, we define an incompatibility score for purely graphical bivariate causal statements, based on global consistency constraints that are derived from acyclicity and faithfulness assumptions. We give theoretical and empirical evidence that both scores can successfully distinguish correct from incorrect causal statements in generic settings. Moreover, we demonstrate the practical applicability of our methods by analyzing causal claims made by large language models. Our work aims to provide a foundation for assessing the reliability of causal information derived from human experts or artificial intelligence in settings where alternative forms of validation are unavailable.
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。
