arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2412.14019cs.AI
收藏

通过不一致知识库检索因果顺序的类别

Retrieving Classes of Causal Orders with Inconsistent Knowledge Bases

Sorbonne Université, INSERM, Institut Pierre Louis d’Epidémiologie et de Santé Publique(索邦大学,法国国家健康与医学研究院,皮埃尔·路易流行病学与公共卫生研究所)

Federico Baldo, Simon Ferreira, Charles K. Assaad

AI总结:

本文提出通过LLM计算变量对一致性分数,构建半完全偏图以提取因果顺序抽象,从而有效恢复正确因果顺序,提供可靠的因果框架。

摘要:

传统因果发现方法往往依赖于强且不可测试的假设,使其在现实应用中不可靠。在这一背景下,大型语言模型(LLMs)作为一种提取文本元数据中因果知识的有希望的替代方案出现,能够有效整合领域专业知识。然而,LLMs容易产生幻觉,需要策略来考虑这些限制。一种有效的方法是使用一致性度量作为可靠性代理。此外,LLMs不能明确区分直接和间接的因果关系,这使得发现因果有向无环图(DAGs)变得复杂,因为这些图通常稀疏。这种模糊性在不同领域中非正式句子的表述中尤为明显。因此,专注于因果顺序提供了一个更实际和直接的任务给LLMs。我们提出了一种新的方法,用于推导因果顺序的抽象,以最大化从LLM获得的一致性分数。我们的方法始于计算变量之间的成对一致性分数,从而构建一个半完全偏图,将这些分数整合到抽象中。使用这种结构,我们识别出一个最大化偏无环图和一个最大化所有配置一致性的最优无环竞赛集。我们进一步展示了如何利用抽象和因果顺序的类别来估计因果效应。我们在流行病学和公共卫生领域的广泛因果DAGs中评估了我们的方法。我们的结果表明,所提出的方法可以有效地恢复正确的因果顺序,提供一个可靠且实用的LLM辅助因果框架。

英文摘要:

Traditional causal discovery methods often depend on strong, untestable assumptions, making them unreliable in real-world applications. In this context, Large Language Models (LLMs) have emerged as a promising alternative for extracting causal knowledge from text-based metadata, effectively consolidating domain expertise. However, LLMs are prone to hallucinations, necessitating strategies that account for these limitations. One effective approach is to use a consistency measure as a proxy of reliability. Moreover, LLMs do not clearly distinguish direct from indirect causal relationships, complicating the discovery of causal Directed Acyclic Graphs (DAGs), which are often sparse. This ambiguity is evident in the way informal sentences are formulated in various domains. For this reason, focusing on causal orders provides a more practical and direct task for LLMs. We propose a new method for deriving abstractions of causal orders that maximizes a consistency score obtained from an LLM. Our approach begins by computing pairwise consistency scores between variables, from which we construct a semi-complete partially directed graph that consolidates these scores into an abstraction. Using this structure, we identify both a maximally oriented partially directed acyclic graph and an optimal set of acyclic tournaments that maximize consistency across all configurations. We further demonstrate how both the abstraction and the class of causal orders can be used to estimate causal effects. We evaluate our method on a wide set of causal DAGs extracted from scientific literature in epidemiology and public health. Our results show that the proposed approach can effectively recover the correct causal order, providing a reliable and practical LLM-assisted causal framework.

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。

↑