New foundation models advance causal discovery from unstructured data · 6 sources tracked
ByPulseAugur Editorial·[9 sources]·
Researchers are developing advanced methods for causal discovery from unstructured data, a complex task in specialized domains like healthcare and finance. Two papers introduce foundation models: DKCD enhances causal discovery by integrating domain knowledge to identify latent factors and improve annotation accuracy, while DAG-FM and CDFM propose general-purpose foundation models that leverage Transformer architectures and variational frameworks to handle heterogeneous causal mechanisms and scale to large datasets. Another paper, IFAR, focuses on multi-perspective and multi-level abductive reasoning for LLMs, achieving significant improvements in identifying causes for pollution and disease.
AI
IMPACT
These advancements in causal discovery could lead to more robust AI systems capable of understanding and reasoning about cause-and-effect relationships in complex data.
RANK_REASON
Multiple research papers introducing new methods and models for causal discovery.
arXiv:2607.09348v1 Announce Type: new Abstract: Causal discovery from unstructured data is a challenging yet underexplored task in high-expertise domains such as healthcare, finance, and education. Existing methods typically leverage the general knowledge of large language models…
Causal discovery from unstructured data is a challenging yet underexplored task in high-expertise domains such as healthcare, finance, and education. Existing methods typically leverage the general knowledge of large language models (LLMs) to identify causal factors from unstruct…
arXiv:2409.05559v2 Announce Type: replace Abstract: Large language models (LLMs) have developed rapidly, and their reasoning capabilities have become a hot research topic. However, there is still limited exploration of abductive reasoning. The multi-perspective and multi-level of…
arXiv stat.ML
TIER_1English(EN)·Yikang Chen, Zhengkang Guan, Haoyuan Qian, Peng Cui, Yi Yang, Kun Kuang·
arXiv:2607.11510v1 Announce Type: cross Abstract: Causal discovery from observational tabular data remains fundamentally challenging, primarily due to the heterogeneity of underlying causal mechanisms and the high-dimensional combinatorial search space of Directed Acyclic Graphs …
arXiv stat.ML
TIER_1English(EN)·M\'aty\'as Schubert, Theofanis Aslanidis, Tom Claassen, Sara Magliacane·
arXiv:2607.10456v1 Announce Type: new Abstract: Expert background knowledge is often available in practical applications of causal discovery. Such constraints on the true causal graph can help causal discovery in terms of identifiability of causal effects and accuracy of the lear…
arXiv:2607.11508v1 Announce Type: cross Abstract: Causal discovery, the process of recovering underlying causal structures from observational data, is a fundamental pursuit across scientific disciplines. Over the past decades, numerous algorithms have been developed to tackle thi…
Causal discovery from observational tabular data remains fundamentally challenging, primarily due to the heterogeneity of underlying causal mechanisms and the high-dimensional combinatorial search space of Directed Acyclic Graphs (DAGs). In this paper, we propose \textbf{DAG-FM},…
Causal discovery, the process of recovering underlying causal structures from observational data, is a fundamental pursuit across scientific disciplines. Over the past decades, numerous algorithms have been developed to tackle this challenge through workflows tailored to the spec…
Expert background knowledge is often available in practical applications of causal discovery. Such constraints on the true causal graph can help causal discovery in terms of identifiability of causal effects and accuracy of the learned structure, but also in reducing the space of…
