arXiv Machine Learning June 5, 2026 By Nirit Nussbaum-Hoffer, Nitay Calderon, Liat Ein-Dor, Roi Reichart

LLM Explainability with Counterfactual Chains and Causal Graphs

Read the original on arXiv Machine Learning →

arXiv:2606. 05972v1 Announce Type: new Abstract: Causal graphs provide a high-level language for making mechanisms transparent.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv AI

Jul 20

Causal-Audit: Explicit and Auditable Graph-based Reasoning via Target-Aware Causal Chain Construction

arXiv:2607. 15281v1 Announce Type: new Abstract: Causal and intervention-based question answering is fundamental to advancing large language models (LLMs) toward reasoning beyond surface-level correlations and understanding underlying causal mechanisms.

By Su Lan, Xuefei Yin, Yanming Zhu, Alan Wee-Chung Liew

llms nlp benchmarks

arXiv AI

Jun 10

Causal Ensemble Agent: Hierarchical Causal Discovery with LLM-guided Expert Reweighting

arXiv:2606. 10607v1 Announce Type: cross Abstract: Causal discovery aims to uncover causal structures from observational data, which is crucial for real-world decision-making.

By Xinyu Li, Yuanyuan Wang, Haoxuan Li, Chuan Zhou, Erdun Gao, Bo Han, Tongliang Liu, Kun Zhang, Howard Bondell, Mingming Gong

llms agents safety

arXiv Machine Learning

Jun 26

Use What You Know: Causal Foundation Models with Partial Graphs

arXiv:2602. 14972v2 Announce Type: replace Abstract: Estimating causal quantities traditionally relies on bespoke estimators tailored to specific assumptions.

By Arik Reuter, Anish Dhir, Cristiana Diaconu, Jake Robertson, Ole Ossen, Frank Hutter, Adrian Weller, Mark van der Wilk, Bernhard Sch\"olkopf

arXiv AI

Aug 12

Leveraging Large Language Models for Causal Discovery: a Constraint-based, Argumentation-driven Approach

arXiv:2602. 16481v2 Announce Type: replace Abstract: Causal discovery seeks to uncover causal relations from data, typically represented as causal graphs, and is essential for predicting the effects of interventions.

By Zihao Li, Fabrizio Russo

llms benchmarks safety

arXiv Machine Learning

Aug 11

CGRL: Causal-Guided Representation Learning for Node-Level Out-of-Distribution Generalization

arXiv:2603. 24304v2 Announce Type: replace-cross Abstract: Graph Neural Networks (GNNs) deliver strong performance on graph tasks, but their accuracy drops significantly under out-of-distribution (OOD) scenarios.

By Bowen Lu, Liangqiang Yang, Teng Li, Kun Zhang

diffusion benchmarks

arXiv AI

Jun 9

Implicit Causal Graph Construction in Text via Chain Discovery

arXiv:2606. 07525v1 Announce Type: cross Abstract: Causal graphs in text are typically populated by observable, predefined events.

By Liesbeth Allein, Marie-Francine Moens

llms

Related stories

Causal-Audit: Explicit and Auditable Graph-based Reasoning via Target-Aware Causal Chain Construction

Causal Ensemble Agent: Hierarchical Causal Discovery with LLM-guided Expert Reweighting

Use What You Know: Causal Foundation Models with Partial Graphs

Leveraging Large Language Models for Causal Discovery: a Constraint-based, Argumentation-driven Approach

CGRL: Causal-Guided Representation Learning for Node-Level Out-of-Distribution Generalization

Implicit Causal Graph Construction in Text via Chain Discovery