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:2404.06349v3 Announce Type: replace Abstract: The ability to understand causality significantly impacts the competence of large language models (LLMs) in output explanation and counterfactual r...
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:2609.06941v1 Announce Type: new Abstract: Causal effect estimation asks how an outcome would change under an intervention, and medicine, economics, and public policy all treat it as a foundatio...
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?
CIDER-FM is a causal foundation model that combines finite observational data with surrogate-interventional datasets to predict target conditional interventional distributions more accurately than using observational data alone. It employs an intervention-aware representation and hierarchical three‑axis attention to integrate information across variables, samples, and experimental regimes. Experiments on synthetic graphs, simulated data, and real‑world Causal Chambers data show that incorporating experimental context improves CID prediction performance.
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.
arXiv:2602. 06337v2 Announce Type: replace-cross Abstract: Causal inference is essential for decision-making but remains challenging for non-experts.
Matryoshka Attribution (MAttr) is a mask‑learning method that identifies nested subsets of a language model’s internal components by minimizing downstream loss. It uses a differentiable sigmoid top‑k operator and randomizes sparsity during training to produce an attribution ordering of components. MAttr tops the Mechanistic Interpretability Benchmark leaderboard and can be applied via reinforcement learning to pinpoint weight changes that control behaviors such as refusal in Llama 3.1 8B Instruct, where restoring just 1% of weights removes refusals while preserving capabilities.