Related papers: ModelWizard: Toward Interactive Model Construction

Topic models are statistical tools that allow their users to gain qualitative and quantitative insights into the contents of textual corpora without the need for close reading. They can be applied in a wide range of settings from discourse…

Human beings possess the most sophisticated computational machinery in the known universe. We can understand language of rich descriptive power, and communicate in the same environment with astonishing clarity. Two of the many contributors…

Model-driven engineering is the automatic production of software artefacts from abstract models of structure and functionality. By targeting a specific class of system, it is possible to automate aspects of the development process, using…

Test-time interventions for language models can enhance factual accuracy, mitigate harmful outputs, and improve model efficiency without costly retraining. But despite a flood of new methods, different types of interventions are largely…

An interactive robot framework accomplishes long-horizon task planning and can easily generalize to new goals and distinct tasks, even during execution. However, most traditional methods require predefined module design, making it hard to…

When language models answer open-ended problems, they implicitly make hidden decisions that shape their outputs, leaving users with uncontextualized answers rather than a working map of the problem; drawing on multiverse analysis from…

As practitioners increasingly deploy machine learning models in critical domains such as health care, finance, and policy, it becomes vital to ensure that domain experts function effectively alongside these models. Explainability is one way…

Providing plausible responses to why questions is a challenging but critical goal for language based human-machine interaction. Explanations are challenging in that they require many different forms of abstract knowledge and reasoning.…

Recent progress in deep learning and natural language processing has given rise to powerful models that are primarily trained on a cloze-like task and show some evidence of having access to substantial linguistic information, including some…

Embedded software is growing fast in size and complexity, leading to intimate mixture of complex architectures and complex control. Consequently, software specification requires modeling both structures and behaviour of systems.…

We introduce a causal modeling framework that captures the input-output behavior of predictive models (e.g., machine learning models). The framework enables us to identify features that directly cause the predictions, which has broad…

We propose a framework for building graphical causal model that is based on the concept of causal mechanisms. Causal models are intuitive for human users and, more importantly, support the prediction of the effect of manipulation. We…

Complex software-driven systems often interleave distributed, concurrent computation processes with physical interactions with the environment. Developing these systems more efficiently and safely can be achieved by employing actionable,…

The growing adoption of foundation models calls for a paradigm shift from Data Science to Model Science. Unlike data-centric approaches, Model Science places the trained model at the core of analysis, aiming to interact, verify, explain,…

Theory-guided machine learning has demonstrated that including authentic domain knowledge directly into model design improves performance, sample efficiency and out-of-distribution generalisation. Yet the process by which a formal domain…

In variable selection, a selection rule that prescribes the permissible sets of selected variables (called a "selection dictionary") is desirable due to the inherent structural constraints among the candidate variables. Such selection rules…

Experimental designs reflect assumptions about variable relationships that determine what causal queries researchers can answer through the experiment. Accounting for and communicating these assumptions is essential for drawing valid,…

The birth of Foundation Models brought unprecedented results in a wide range of tasks, from language to vision, to robotic control. These models are able to process huge quantities of data, and can extract and develop rich representations,…

Topic modeling is an unsupervised method for revealing the hidden semantic structure of a corpus. It has been increasingly widely adopted as a tool in the social sciences, including political science, digital humanities and sociological…

Efficiently navigating complex environments requires agents to internalize the underlying logic of their world, yet standard world modelling methods often struggle with sample inefficiency, lack of transparency, and poor scalability. We…