arXiv:2603. 01372v2 Announce Type: replace-cross Abstract: Concept Bottleneck Models (CBMs) enhance the interpretability of end-to-end neural networks by introducing a layer of concepts and predicting the class label from the concept predictions.
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.
arXiv:2607. 08349v1 Announce Type: new Abstract: Mechanistic interpretability often evaluates explanations by intervening on a model: swapping hidden states, patching activations, ablating components, or comparing a compressed model to the original one.
arXiv:2510. 05750v2 Announce Type: replace-cross Abstract: Graph neural networks (GNNs) have achieved remarkable success in node classification.
arXiv:2606. 05972v1 Announce Type: new Abstract: Causal graphs provide a high-level language for making mechanisms transparent.
arXiv:2510. 12957v4 Announce Type: replace-cross Abstract: We treat the internals of generative models as mechanistic objects rather than black boxes.
arXiv:2602. 24266v2 Announce Type: replace-cross Abstract: Which internal mechanisms of a neural network can be replaced while preserving the computation it performs?
arXiv:2602. 06337v2 Announce Type: replace-cross Abstract: Causal inference is essential for decision-making but remains challenging for non-experts.
arXiv:2608. 03772v1 Announce Type: new Abstract: Explaining the predictions of neural networks is a central challenge in trustworthy AI.
arXiv:2510. 21457v2 Announce Type: replace Abstract: Estimating heterogeneous treatment effects in network settings is complicated by interference, meaning that the outcome of an instance can be influenced by the treatment status of others.
arXiv:2605. 15133v2 Announce Type: replace Abstract: Causal inference, estimating causal effects from observational data, is a fundamental tool in many disciplines.
arXiv:2602. 20094v2 Announce Type: replace Abstract: As large language models (LLMs) witness increasing deployment in complex, high-stakes decision-making scenarios, it becomes imperative to ground their reasoning in causality rather than spurious correlations.
arXiv:2608. 15382v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly proposed for healthcare decision support, but their evaluations still reward single-answer accuracy rather than reasoning about interventions, mechanisms, harms, evidence, and uncertainty.