Results 261 to 270 of about 1,964,226 (308)

Multi-Agent Causal Discovery Using Large Language Models

arXiv.org
Causal discovery aims to identify causal relationships between variables and is a critical research area in machine learning. Traditional methods focus on statistical or machine learning algorithms to uncover causal links from structured data, often ...
Hao Duong Le, Xin Xia, Zhang Chen
semanticscholar   +1 more source

MECD: Unlocking Multi-Event Causal Discovery in Video Reasoning

Neural Information Processing Systems
Video causal reasoning aims to achieve a high-level understanding of video content from a causal perspective. However, current video reasoning tasks are limited in scope, primarily executed in a question-answering paradigm and focusing on short videos ...
Tieyuan Chen, Huabin Liu, Tianyao He, Yihang Chen, Chaofan Gan, Xiao Ma, Cheng Zhong, Yang Zhang, Yingxue Wang, Hui Lin, Weiyao Lin   +10 more
semanticscholar   +1 more source

Large Language Models for Constrained-Based Causal Discovery

arXiv.org
Causality is essential for understanding complex systems, such as the economy, the brain, and the climate. Constructing causal graphs often relies on either data-driven or expert-driven approaches, both fraught with challenges.
Kai-Hendrik Cohrs, Gherardo Varando, Emiliano Díaz, Vasileios Sitokonstantinou, G. Camps-Valls   +4 more
semanticscholar   +1 more source

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

International Joint Conference on Artificial Intelligence
Causal discovery (CD) and Large Language Models (LLMs) have emerged as transformative fields in artificial intelligence that have evolved largely independently.
Guangya Wan, Yunsheng Lu, Yuqi Wu, Mengxuan Hu, Sheng Li   +4 more
semanticscholar   +1 more source

Signature Kernel Conditional Independence Tests in Causal Discovery for Stochastic Processes

International Conference on Learning Representations
Inferring the causal structure underlying stochastic dynamical systems from observational data holds great promise in domains ranging from science and health to finance. Such processes can often be accurately modeled via stochastic differential equations
Georg Manten, Cecilia Casolo, E. Ferrucci, S. W. Mogensen, C. Salvi, Niki Kilbertus   +5 more
semanticscholar   +1 more source

On the Reliability of Large Language Models for Causal Discovery

Annual Meeting of the Association for Computational Linguistics
This study investigates the efficacy of Large Language Models (LLMs) in causal discovery. Using newly available open-source LLMs, OLMo and BLOOM, which provide access to their pre-training corpora, we investigate how LLMs address causal discovery through
Tao Feng, Lizhen Qu, Niket Tandon, Zhuang Li, Xiaoxi Kang, Gholamreza Haffari   +5 more
semanticscholar   +1 more source

Comprehensive Review and Empirical Evaluation of Causal Discovery Algorithms for Numerical Data

arXiv.org
Causal analysis has become an essential component in understanding the underlying causes of phenomena across various fields. Despite its significance, existing literature on causal discovery algorithms is fragmented, with inconsistent methodologies, i.e.,
Wenjin Niu, Zijun Gao, Liyan Song, Lingbo Li   +3 more
semanticscholar   +1 more source

The Landscape of Causal Discovery Data: Grounding Causal Discovery in Real-World Applications

CLEaR
Causal discovery aims to automatically uncover causal relationships from data, a capability with significant potential across many scientific disciplines. However, its real-world applications remain limited.
Philippe Brouillard, C. Squires, Jonas Wahl, K. Kording, Karen Sachs, Alexandre Drouin, Dhanya Sridhar   +6 more
semanticscholar   +1 more source

Sample, estimate, aggregate: A recipe for causal discovery foundation models

Trans. Mach. Learn. Res.
Causal discovery, the task of inferring causal structure from data, has the potential to uncover mechanistic insights from biological experiments, especially those involving perturbations.
Menghua Wu, Yujia Bao, R. Barzilay, T. Jaakkola   +3 more
semanticscholar   +1 more source

Federated Causal Discovery from Heterogeneous Data

International Conference on Learning Representations
Conventional causal discovery methods rely on centralized data, which is inconsistent with the decentralized nature of data in many real-world situations.
Loka Li, Ignavier Ng, Gongxu Luo, Biwei Huang, Guan-Hong Chen, Tongliang Liu, Bin Gu, Kun Zhang   +7 more
semanticscholar   +1 more source