English
Related papers

Related papers: Towards Error-Centric Intelligence II: Energy-Stru…

200 papers

Explanations in interactive machine-learning systems facilitate debugging and improving prediction models. However, the effectiveness of various global model-centric and data-centric explanations in aiding domain experts to detect and…

Artificial Intelligence · Computer Science 2024-02-02 Aditya Bhattacharya , Simone Stumpf , Lucija Gosak , Gregor Stiglic , Katrien Verbert

Despite surpassing human performance across mathematics, coding, and other knowledge-intensive tasks, large language models (LLMs) continue to struggle with causal reasoning. A core obstacle is the target data itself: causal systems are…

Artificial Intelligence · Computer Science 2026-05-12 Nicolás Astorga , Anita Kriz , Mihaela van der Schaar

Interpretability research on large language models (LLMs) has yielded important insights into model behaviour, yet recurring pitfalls persist: findings that do not generalise, and causal interpretations that outrun the evidence. Our…

Machine Learning · Computer Science 2026-03-20 Shruti Joshi , Aaron Mueller , David Klindt , Wieland Brendel , Patrik Reizinger , Dhanya Sridhar

Counterfactual explanations offer an intuitive and straightforward way to explain black-box models and offer algorithmic recourse to individuals. To address the need for plausible explanations, existing work has primarily relied on…

Machine Learning · Computer Science 2023-12-19 Patrick Altmeyer , Mojtaba Farmanbar , Arie van Deursen , Cynthia C. S. Liem

Much of our experiments are designed to uncover the cause(s) and effect(s) behind a data generating mechanism (i.e., phenomenon) we happen to be interested in. Uncovering such relationships allows us to identify the true working of a…

Machine Learning · Computer Science 2023-07-11 M. Z. Naser

Large language models (LLMs) enable waveform-to-text ECG interpretation and interactive clinical questioning, yet most ECG-LLM systems still rely on weak signal-text alignment and retrieval without explicit physiological or causal…

Machine learning models have had discernible achievements in a myriad of applications. However, most of these models are black-boxes, and it is obscure how the decisions are made by them. This makes the models unreliable and untrustworthy.…

Machine Learning · Computer Science 2020-03-23 Raha Moraffah , Mansooreh Karami , Ruocheng Guo , Adrienne Raglin , Huan Liu

Despite the recent success of neural network models in mimicking animal performance on visual perceptual tasks, critics worry that these models fail to illuminate brain function. We take it that a central approach to explanation in systems…

Neurons and Cognition · Quantitative Biology 2021-04-13 Rosa Cao , Daniel Yamins

Interventional causal models describe several joint distributions over some variables used to describe a system, one for each intervention setting. They provide a formal recipe for how to move between the different joint distributions and…

Machine Learning · Statistics 2021-08-06 Eigil F. Rischel , Sebastian Weichwald

Recent developments enable the quantification of causal control given a structural causal model (SCM). This has been accomplished by introducing quantities which encode changes in the entropy of one variable when intervening on another.…

Machine Learning · Computer Science 2024-02-20 Francisco N. F. Q. Simoes , Mehdi Dastani , Thijs van Ommen

Structural Causal Models (SCMs) offer a principled framework to reason about interventions and support out-of-distribution generalization, which are key goals in scientific discovery. However, the task of learning SCMs from observed data…

Machine Learning · Computer Science 2026-04-06 Divyat Mahajan , Jannes Gladrow , Agrin Hilmkil , Cheng Zhang , Meyer Scetbon

Mechanistic interpretability aims to explain neural model behaviour by reverse-engineering learned computational structure into human-understandable components. Without a formal framework, however, mechanistic explanations cannot be…

Machine Learning · Computer Science 2026-05-12 Ward Gauderis , Thomas Dooms , Steven T. Holmer , Kola Ayonrinde , Geraint A. Wiggins

The domain of explainable AI is of interest in all Machine Learning fields, and it is all the more important in clustering, an unsupervised task whose result must be validated by a domain expert. We aim at finding a clustering that has high…

Artificial Intelligence · Computer Science 2024-03-28 Mathieu Guilbert , Christel Vrain , Thi-Bich-Hanh Dao

We describe basic ideas underlying research to build and understand artificially intelligent systems: from symbolic approaches via statistical learning to interventional models relying on concepts of causality. Some of the hard open…

Artificial Intelligence · Computer Science 2022-04-04 Bernhard Schölkopf , Julius von Kügelgen

Recovering the structure of causal graphical models from observational data is an essential yet challenging task for causal discovery in scientific scenarios. Domain-specific causal discovery usually relies on expert validation or prior…

Artificial Intelligence · Computer Science 2025-08-27 Taiyu Ban , Lyuzhou Chen , Derui Lyu , Xiangyu Wang , Qinrui Zhu , Qiang Tu , Huanhuan Chen

With recent progress on fine-tuning language models around a fixed sparse autoencoder, we disentangle the decoder matrix into almost orthogonal features. This reduces interference and superposition between the features, while keeping…

Machine Learning · Computer Science 2026-02-05 Moritz Miller , Florent Draye , Bernhard Schölkopf

Learning causal representations from observational and interventional data in the absence of known ground-truth graph structures necessitates implicit latent causal representation learning. Implicit learning of causal mechanisms typically…

Machine Learning · Computer Science 2024-08-19 Shayan Shirahmad Gale Bagi , Zahra Gharaee , Oliver Schulte , Mark Crowley

Three distinct phenomena complicate statistical causal analysis: latent common causes, causal cycles, and latent selection. Foundational works on Structural Causal Models (SCMs), e.g., Bongers et al. (2021, Ann. Stat., 49(5): 2885-2915),…

Methodology · Statistics 2025-11-23 Leihao Chen , Onno Zoeter , Joris M. Mooij

Pearl observes that causal knowledge enables predicting the effects of interventions, such as actions, whereas descriptive knowledge only permits drawing conclusions from observation. This paper extends Pearl's approach to causality and…

Artificial Intelligence · Computer Science 2025-07-08 Kilian Rückschloß , Felix Weitkämper

There exist well-developed frameworks for causal modelling, but these require rather a lot of human domain expertise to define causal variables and perform interventions. In order to enable autonomous agents to learn abstract causal models…

Artificial Intelligence · Computer Science 2022-08-15 Taco Cohen