Causal Foundation Models (CFMs) are pretrained neural networks designed to estimate causal quantities—such as the average treatment effect—across new datasets using in‑context learning, eliminating the need for bespoke pipelines or model updates. The paper introduces CFMs, reviews foundational concepts in causal inference and machine learning, and provides practical code examples and Jupyter notebooks to illustrate their application.
CausalArena is a new benchmark designed to evaluate causal discovery methods in the era of foundation models. It unifies synthetic structural causal models (SCMs), semantically grounded SCMs, and formula‑grounded SCMs, while also including real‑world datasets for external validation. Experiments show that performance rankings vary widely across different SCM families and protocols, indicating that strong results on one benchmark do not necessarily transfer to others.
arXiv:2609.37446v1 Announce Type: new Abstract: Supervised causal discovery learns to infer causal structure for a new dataset from training datasets paired with structural labels. These training pai...
arXiv:2507. 14661v2 Announce Type: replace-cross Abstract: Semi-supervised domain adaptation (SSDA) seeks to achieve accurate predictions in a target domain with limited labeled target data by exploiting abundant source and unlabeled target data.
TabCausal is a causal discovery foundation model that learns to map datasets directly to causal graphs by pretraining across diverse causal environments. It uses a dynamic task construction strategy to expose the model to varied graph priors, mechanisms, noise models, dimensions, sample sizes, and intervention regimes, improving transferability from observational and mixed‑interventional data. On large synthetic benchmarks and a new protocol‑guided semantic benchmark, TabCausal outperforms many classical baselines and shows robust structure recovery, especially when interventional evidence is available.
The paper introduces causal foundation models that can bound the effects of interventions and counterfactuals using only observational data. It defines a canonical prior with full support over structural causal models with discrete observables, enabling the translation of counterfactual bounding into learning distributions over functions that map data and structural assumptions to causal queries. This approach extends causal foundational modelling to partially-identifiable causal effects, where unobserved confounding leads to multiple compatible values for the effect.
CausalArena is a unified, evolvable benchmark designed to evaluate causal discovery methods across diverse structural causal models (SCMs). It incorporates synthetic SCMs for controlled structural variation, semantic operational SCMs for human-auditable environments, and formula-grounded SCMs to test discovery under explicit scientific mechanisms, along with real-world datasets for external validity. Experiments show that performance rankings vary significantly across SCM families and protocols, indicating that strong results on one benchmark do not generalize to others, especially in the context of causal discovery foundation models.
arXiv:2606. 26467v1 Announce Type: new Abstract: We introduce TabPFN-CFM, a causal foundation model that can handle multiple causal problems.
arXiv:2602. 14972v2 Announce Type: replace Abstract: Estimating causal quantities traditionally relies on bespoke estimators tailored to specific assumptions.
CausalProfiler is a synthetic benchmark generator designed to evaluate causal machine learning (Causal ML) methods more rigorously and transparently. It randomly samples causal models, data, queries, and ground truths based on explicit design choices across observation, intervention, and counterfactual reasoning levels, providing coverage guarantees and transparent assumptions. The authors demonstrate its utility by testing several state‑of‑the‑art methods under diverse conditions, both within and outside the identification regime, highlighting the insights CausalProfiler can reveal.
arXiv:2607. 21806v1 Announce Type: new Abstract: Predictive machine learning (ML) models are increasingly used to aid human decision-makers across various high-risk domains such as healthcare and criminal justice.
The study evaluates 12 instruction‑tuned open‑weight LLMs on six causal‑graph benchmarks, testing five prompting strategies and four confidence sources. Findings show that LLMs tend to over‑predict edges, misclassify indirect or reversed edges as direct, and exhibit high over‑confidence, while conventional confidence estimates are unreliable and agreement signals offer limited improvement. The results suggest LLMs should be used as externally validated soft causal priors rather than definitive causal‑structure evidence.