I don't trust you, explain yourself!bookmark_border

While data visualization has historically focused on revealing frequencies, correlations, and other descriptive patterns, relying on descriptive statistics alone during exploratory data analysis may lead to spurious conclusions. Consequently, Visual Causal Inference (VCI) has emerged as a critical research topic, combining data visualization, an understanding of human perception and cognition, human-computer interaction, and the rigor of statistical causal inference and modeling. Reflecting the broad applicability of such work, the literature surrounding VCI has addressed a variety of research questions, fragmented across different contribution types, venues, and application domains. This paper provides the first systematic review of the VCI landscape and proposes a taxonomy for structuring the domain across three core categories: the Structural Pillar, examining interactive visual analytics techniques with a graphical structure presenting causal structures; the Augmentative Pillar, exploring techniques to estimate causal effects using auxiliary representations; and the Cognitive Pillar, studying how humans perceive and comprehend causality from visualizations. By synthesizing these areas, we map the current design space and identify critical gaps and emerging opportunities in VCI, calling for future actions in unifying the pillars, navigating design trade-offs, and bridging the evaluation gap for better visual communication of causality.

Data-driven journalism and policy reports frequently rely on statements grounded in statistical evidence, referred to as data claims. Verifying such a claim requires connecting it to the underlying structured dataset. However, existing systems typically isolate automated fact-checking from manual data exploration, leaving it unclear how readers coordinate AI assistance with manual inspection of the evidence in practice. We present FYI, a browser extension that embeds fact-checking in the reading environment, and use it as a design probe to study how people detect, verify, and determine the validity of data claims against the underlying dataset. FYI provides four complementary tools spanning the spectrum from full automation to manual data exploration. In an exploratory study (N=22), participants used FYI to fact-check claims in a data-driven article. We find that participants adopted three distinct workflow archetypes—AI-first with manual confirmation, manual-first with AI supplement, and parallel co-review—with visualization serving as the primary mechanism for auditing AI conclusions. Trust in AI shifted dynamically, growing when multiple tools converged and eroding when AI outputs were inconsistent. These findings suggest that fact-checking systems should treat AI as a starting point that human verification complements rather than a definitive authority, elevate visualization as a core verification capability, and support flexible, user-driven workflows. We release FYI as open-source software for further research at https://github.com/DataVisards/FYI.

Large language models increasingly generate summaries from collections of documents to support sensemaking and reporting, but verifying whether summary statements are grounded in source materials remains difficult. In multi-document summarization (MDS), evidence is distributed across many source documents and may be incomplete, conflicting, or missing. We present Summary Verification Space (SVS), a visual analytics system for verifying multi-document summaries through spatial document organization and coordinated provenance visualization. To support scalable verification, we investigate two alternative 2D canvas layouts: a SUMMARY-GUIDED layout that organizes documents by alignment with summary sentences, and a SOURCE-GUIDED layout that arranges documents by semantic similarity. Coordinated provenance visualization then makes relationships among summary content, source documents, and supporting evidence explicit, enabling users to trace support, contradiction, and missing evidence during verification. A task-driven usage scenario illustrates an auditing workflow in which users utilize the layouts to locate relevant documents and coverage gaps, then inspect linked claims and source evidence to make their own grounding judgments. In a comparative study with provenance held constant, both spatial layouts improved aggregate accuracy and reduced workload relative to a linear baseline, with the clearest gains on relevance tasks. The SUMMARY-GUIDED layout provides the strongest overall balance of accuracy, efficiency, confidence, and workload.

Exploratory Data Analysis (EDA) systems extract and present data facts to summarize meaningful patterns such as trends and correlations for efficient dataset exploration. However, existing approaches rarely consider outlier detection at the level of data facts, and heterogeneous facts from different analytical scopes are often aggregated in a single view, making it difficult to define meaningful metrics and effectively analyze data fact outliers. To fill this gap, we present FOX, a novel visual analytics system for interactive data Fact Outlier eXploration. FOX organizes data facts into groups with consistent analytical scopes and computes a unified outlier score that combines distribution-based and pattern-based components. Its interface comprises an Upload Panel for data preparation and two coordinated exploration panels: the Overview Panel employs a matrix-based visualization to enable an intuitive overview of all data facts, and the Main Panel provides four linked views for cluster-level and fact-level analysis. We evaluated the usability and effectiveness of the system through two usage scenarios on public datasets and in-depth interviews with 12 participants. The results show that FOX enables meaningful detection, analysis, and explanation of data fact outliers.

Trust plays a critical role in visual data communication and decision-making, yet existing visualization research employs varied trust measures, making it challenging to compare and synthesize findings across studies. In this work, we first took a bottom-up, data-driven approach to understand what visualization readers mean when they say they "trust" a visualization. We compiled and adapted a broad set of trust-related statements from existing inventories and collected responses to visualizations with varying degrees of trustworthiness. Through exploratory factor analysis, we derived an operational definition of trust in visualizations. Our findings indicate that people perceive a trustworthy visualization as one that presents credible information and is comprehensible and usable. Building on this insight, we developed an eight-item inventory: four core items measuring trust in visualizations and four optional items controlling for individual differences in baseline trust tendency. We established the inventory's internal consistency reliability using McDonald's omega, confirmed its content validity by demonstrating alignment with theoretically-grounded trust dimensions, and validated its criterion validity through two trust games with real-world stakes. Finally, we illustrate how this standardized inventory can be applied across diverse visualization research contexts. Utilizing our inventory, future research can examine how design choices, tasks, and domains influence trust, and how to foster appropriate trusting behavior in human-data interactions.

Dimensionality Reduction (DR) is a fundamental tool for high-dimensional data exploration, reducing the complexity of latent spaces of machine learning models, and assisting in the explanation of complex %black-box opaque models. However, non-linear DR techniques %operate as black boxes often function as opaque transformations themselves, making it challenging to understand how individual features influence instance positioning in the reduced space. This lack of transparency complicates the analysis and interpretation of structural patterns, hindering the ability to reason about the organization of high-dimensional data based on the projected layout. In order to address this challenge, dimensionality reduction explanation methods have shown promise in improving the understanding of the observed groups and cluster structures. Unfortunately, existing DR explanation approaches tend to suffer from limitations such as multiple attributions per feature and restricted applicability to specific dimensionality reduction methods, which hinder their use. In this work, we propose FADEx, a novel local per-instance feature attribution method that leverages local linear approximation via first-order Taylor expansion and Singular Value Decomposition to provide explanations. FADEx computes the local linear models via weighted least squares, eliminating the need for out-of-sample data mapping, making it agnostic to the DR method, while simultaneously providing local feature attributions and distortion analysis. Through qualitative and quantitative evaluations, comparisons with existing methods, and case studies, we demonstrate FADEx's effectiveness and versatility in providing explanations and analytical resources for analyzing the behavior of DR methods. The results indicate FADEx yields robust and reliable explanations, outperforming existing approaches in several aspects.

Rule-based machine learning models, including those derived from decision trees or forests, are often considered inherently interpretable. However, human understanding is hindered by model size, rule complexity, and interdependencies between features. Moreover, rule sets extracted from ensemble models can contain contradictory, incomplete, or counterintuitive logic, even when the overall model achieves high predictive accuracy. This paper introduces a visual analytics methodology designed to support systematic exploration of rule-based model logic and its alignment with domain knowledge. Our approach integrates overview visualizations, interactive filtering, contradiction analysis, and topic modeling. This enables analysts to detect illogical or implausible rules, assess their potential impact, and refine the model to improve its interpretability and trustworthiness. A key distinction of our method is its ability to support reasoning about model behavior both with and without access to labeled data. We demonstrate the approach through two real-world case studies: evaluating logical consistency in a vessel movement classifier and analyzing feature relationships in a COVID-19 prediction model. These studies show how visual analytics can facilitate logic-focused model critique beyond traditional performance metrics and enable valuable domain-relevant insights.