Related papers: Visual Reasoning Strategies for Effect Size Judgme…

We present a randomized controlled trial for a model-in-the-loop regression task, with the goal of measuring the extent to which (1) good explanations of model predictions increase human accuracy, and (2) faulty explanations decrease human…

Graphical perception studies typically measure visualization encoding effectiveness using the error of an "average observer", leading to canonical rankings of encodings for numerical attributes: e.g., position > area > angle > volume. Yet…

Providing system-generated explanations for recommendations represents an important step towards transparent and trustworthy recommender systems. Explainable recommender systems provide a human-understandable rationale for their outputs.…

Measuring uncertainties in the output of a deep learning method is useful in several ways, such as in assisting with interpretation of the outputs, helping build confidence with end users, and for improving the training and performance of…

Uncertainty estimation is critical for deploying reasoning language models, yet remains poorly understood under extended chain-of-thought reasoning. We study parallel sampling as a fully black-box approach using verbalized confidence and…

Practitioners making decisions based on causal effects typically ignore structural uncertainty. We analyze when this uncertainty is consequential enough to warrant methodological solutions (Bayesian model averaging over competing causal…

Uncertainty estimation has been widely studied in medical image segmentation as a tool to provide reliability, particularly in deep learning approaches. However, previous methods generally lack effective supervision in uncertainty…

For safe operation, a robot must be able to avoid collisions in uncertain environments. Existing approaches for motion planning under uncertainties often assume parametric obstacle representations and Gaussian uncertainty, which can be…

The ability to identify and resolve uncertainty is crucial for the robustness of a dialogue system. Indeed, this has been confirmed empirically on systems that utilise Bayesian approaches to dialogue belief tracking. However, such systems…

Visually-aware recommendation on E-commerce platforms aims to leverage visual information of items to predict a user's preference. It is commonly observed that user's attention to visual features does not always reflect the real preference.…

Line attributes such as width and dashing are commonly used to encode information. However, many questions on the perception of line attributes remain, such as how many levels of attribute variation can be distinguished or which line…

Rule sets are often used in Machine Learning (ML) as a way to communicate the model logic in settings where transparency and intelligibility are necessary. Rule sets are typically presented as a text-based list of logical statements…

Generalizable robotic mobile manipulation in open-world environments poses significant challenges due to long horizons, complex goals, and partial observability. A promising approach to address these challenges involves planning with a…

Visualization research tends to de-emphasize consideration of the textual context in which its images are placed. We argue that visualization research should consider textual representations as a primary alternative to visual options when…

Visualizations are common methods to convey information but also increasingly used to spread misinformation. It is therefore important to understand the factors people use to interpret visualizations. In this paper, we focus on factors that…

Explainability and uncertainty quantification are key to trustable artificial intelligence. However, the reasoning behind uncertainty estimates is generally left unexplained. Identifying the drivers of uncertainty complements explanations…

Visualizations such as bar charts, scatter plots, and objects on geographical maps often convey critical information, including exact and relative numeric values, using shapes. The choice of shape and method of encoding information is often…

In this provocation, we suggest that much (although not all) current uncertainty visualization simplifies the myriad forms of uncertainty into error bars around an estimate. This apparent simplification into error bars comes only as a…

Discontinuities can be fairly arbitrary but also cause a significant impact on outcomes in larger systems. Indeed, their arbitrariness is why they have been used to infer causal relationships among variables in numerous settings. Regression…

Subset selection-based methods are widely used to explain deep vision models: they attribute predictions by highlighting the most influential image regions and support object-level explanations. While these methods perform well in…