arXiv AI
Jul 10
How Causal Abstraction Underpins Computational Explanation
arXiv:2508. 11214v2 Announce Type: replace-cross Abstract: Explanations of cognitive behavior often appeal to computations over representations.
xWhyL: Causal Interactive Learning
Related stories
arXiv AI
Jun 24
An Introduction to Causal Reinforcement Learning
arXiv:2606. 24160v1 Announce Type: new Abstract: Causal inference provides a set of principles and tools that allow one to combine data and knowledge about an environment to reason with questions of counterfactual nature, i.
arXiv AI
Aug 14
A Unifying Perspective on Causal World Models: From Observations to Representations to Structure
arXiv:2608. 13456v1 Announce Type: new Abstract: World Models (WM) are increasingly seen as a foundation for intelligent agents that can predict, plan, and act beyond their training distribution.
arXiv AI
Jun 16
A Definition of Good Explanations and the Challenges Explaining LLM Outputs
arXiv:2606. 14838v1 Announce Type: new Abstract: How to define a good explanation is a long-standing philosophical debate which has found recent renewed interest in the context of AI outputs.
Hugging Face Trending Papers
Jun 23
An Introduction to Causal Reinforcement Learning
Causal inference provides a set of principles and tools that allow one to combine data and knowledge about an environment to reason with questions of counterfactual nature, i. e.
arXiv AI
Aug 25
Reconciling Consistency-Based Diagnosis with Actual-Causality-Based Explanations
The paper establishes connections between Consistency-Based Diagnosis (CBD) and concepts of Actual Causality and Causal Responsibility from the perspective of Explainable AI (XAI). It highlights that CBD has received limited attention within the XAI community and suggests that linking these areas could positively influence both XAI and Explainable Data Management.
Hugging Face Trending Papers
Aug 13
A Unifying Perspective on Causal World Models: From Observations to Representations to Structure
World Models (WM) are increasingly seen as a foundation for intelligent agents that can predict, plan, and act beyond their training distribution. In this paper, we study WMs from a causal perspective across multiple levels of abstraction, ranging from perceptual observations to building a conceptual representation of the structure governing the environment dynamics.
arXiv AI
Sep 4
A Computationally Feasible Framework for Causal Probabilistic Explanation
The paper introduces Probabilistic Causal Impact (PCI), a framework that blends actual causality (AC) with Pearl’s probability of necessity and sufficiency to provide tractable, causally grounded explanations. PCI reframes explainability as an estimation problem on a probabilistic causal model, enabling efficient approximation via Monte Carlo sampling. The authors evaluate PCI on synthetic and real-world data, demonstrating consistency with AC, scalability, and applicability to complex continuous systems and large-scale causal machine learning models.
arXiv Machine Learning
Aug 27
Towards A Unified Information Bottleneck Framework for Time Series Explanations
arXiv:2608. 25897v1 Announce Type: new Abstract: Explaining deep learning models operating on time series data is crucial in various applications that require transparent and interpretable insights into model behavior.
arXiv AI
Sep 4
Symmetries and Causality: Causal Effect Identification Beyond IID Data
The paper introduces a formal framework that uses symmetries in data to keep causal mechanisms invariant, providing a simple and general mathematical language for causal reasoning. It outlines how to describe models and queries, and presents strategies for rigorously identifying causal effects from data within this framework. The approach reproduces known results for IID data and extends causal analysis to non‑IID settings, complex queries beyond do‑ or soft‑interventions, and incorporates missing data, transfer, and robustness considerations.
arXiv AI
Jun 11
The Impossibility of Eliciting Latent Knowledge
arXiv:2606. 12268v1 Announce Type: new Abstract: Advanced AI systems have extensive knowledge of their environments; in fact, their knowledge may (far) exceed that of their developers or users.
arXiv AI
Aug 12
Rule of Thumb: Explaining Artificial Intelligence Systems using Partial Information
arXiv:2608. 10766v1 Announce Type: new Abstract: Explainable Artificial Intelligence (XAI) seeks to explain how an Artificial Intelligence (AI) system arrived at a particular decision.