利用大语言模型进行因果发现：一种基于约束和论证的方法
Leveraging Large Language Models for Causal Discovery: a Constraint-based, Argumentation-driven Approach
AI总结：
本文提出利用大语言模型作为不完美的专家，结合语义结构先验和条件独立性证据，实现因果发现的先进方法。
摘要：
因果发现旨在从数据中揭示因果关系，通常表示为因果图，并对预测干预效果至关重要。虽然专家知识是构建原则性因果图所必需的，但许多统计方法已提出利用观测数据，具有不同形式的保证。因果假设论证（ABA）是一种框架，利用符号推理确保输入约束与输出图之间的一致性，同时提供一种将数据与专业知识结合的系统方法。我们探索了将大语言模型（LLMs）作为不完美的专家用于因果ABA，从变量名称和描述中提取语义结构先验，并将其与条件独立性证据相结合。在标准基准和语义基础的合成图上进行的实验显示了最先进的性能，我们还引入了一种评估协议，以在评估LLMs进行因果发现时减轻记忆偏差。
英文摘要：
Causal discovery seeks to uncover causal relations from data, typically represented as causal graphs, and is essential for predicting the effects of interventions. While expert knowledge is required to construct principled causal graphs, many statistical methods have been proposed to leverage observational data with varying formal guarantees. Causal Assumption-based Argumentation (ABA) is a framework that uses symbolic reasoning to ensure correspondence between input constraints and output graphs, while offering a principled way to combine data and expertise. We explore the use of large language models (LLMs) as imperfect experts for Causal ABA, eliciting semantic structural priors from variable names and descriptions and integrating them with conditional-independence evidence. Experiments on standard benchmarks and semantically grounded synthetic graphs demonstrate state-of-the-art performance, and we additionally introduce an evaluation protocol to mitigate memorisation bias when assessing LLMs for causal discovery.
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。
