arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.11068cs.CLcs.AI
收藏

用于因果发现的大语言模型:当前格局与未来方向

Large Language Models for Causal Discovery: Current Landscape and Future Directions

School of Data Science, University of Virginia(弗吉尼亚大学数据科学学院);University of Chicago(芝加哥大学);University of Alberta(阿尔伯塔大学)

Guangya Wan, Yunsheng Lu, Yuqi Wu, Mengxuan Hu, Sheng Li

AI总结:

本文综述 LLM 在因果发现中的三类应用路径,分析其增强传统方法的潜力与局限,并提出评估基准和未来研究方向。

摘要:

因果发现(CD)与大语言模型(LLM)已成为人工智能中具有变革性的两个领域,并且在很大程度上是各自独立发展的。CD 专注于从数据中揭示因果关系,而 LLM 擅长自然语言处理与生成,二者的融合为推进因果理解提供了独特机遇。本综述考察了 LLM 如何在三个关键维度上变革 CD:从文本中直接提取因果关系、将领域知识整合到统计方法中,以及精炼因果结构。我们系统分析了利用 LLM 完成 CD 任务的方法,重点说明它们如何创新性地使用元数据和自然语言进行因果推断。分析表明,LLM 既有增强传统 CD 方法的潜力,也存在作为不完美专家系统的当前局限。我们识别了关键研究空白,概述了基于 LLM 的因果发现的评估框架和基准,并倡导未来在因果性研究中利用 LLM。作为对 LLM 与 CD 协同作用的首次全面考察,本工作为该领域的未来进展奠定了基础。

英文摘要:

Causal discovery (CD) and Large Language Models (LLMs) have emerged as transformative fields in artificial intelligence that have evolved largely independently. While CD specializes in uncovering cause-effect relationships from data, and LLMs excel at natural language processing and generation, their integration presents unique opportunities for advancing causal understanding. This survey examines how LLMs are transforming CD across three key dimensions: direct causal extraction from text, integration of domain knowledge into statistical methods, and refinement of causal structures. We systematically analyze approaches that leverage LLMs for CD tasks, highlighting their innovative use of metadata and natural language for causal inference. Our analysis reveals both LLMs' potential to enhance traditional CD methods and their current limitations as imperfect expert systems. We identify key research gaps, outline evaluation frameworks and benchmarks for LLM-based causal discovery, and advocate future research efforts for leveraging LLMs in causality research. As the first comprehensive examination of the synergy between LLMs and CD, this work lays the groundwork for future advances in the field.

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。

↑