arXiv subjects

Grace Guo

Publications and source records attributed to Grace Guo.

14 recordsLinked to original sources

arXiv2026

RaivenTracks: Branching Provenance for Conversational Visualization Workflows

As AI agents increasingly participate in scientific workflows, scientists are shifting from direct authorship toward oversight, inspection, and steering. LLM-driven visualization systems are a promising interface for this hand-off, yet they remain largely stateless, forcing users to reconstruct context across refinements and offering little support for revisiting prior decisions or exploring alternatives. We present RaivenTracks, a workflow-aware extension of the Raiven DSL-mediated visualization pipeline that treats validated visualization specifications as persistent, branchable checkpoints. Because each checkpoint is a verifiable RaivenDSL specification rather than a dialogue transcript, restoring a node recompiles a known artifact rather than re-interpreting prior context. RaivenTracks contributes a two-level state management architecture that pairs a persistent, branchable version tree with a fine-grained undo/redo stack over runtime visualization settings, across both InfoVis and SciVis backends. A formative pilot study with three visualization researchers shows early promise, with all participants adopting the version tree for branching and recovery, and surfaces design directions for tree navigation, node labeling, and scalability that inform a planned controlled comparison against Raiven without version history. We frame branchable conversational visualization history as a step toward provenance support for future scientist-in-the-loop oversight of AI-driven scientific workflows.

cs.HC↗

arXiv2026

Bias at the End of the Score

Reward models (RMs) are inherently non-neutral value functions designed and trained to encode specific objectives, such as human preferences or text-image alignment. RMs have become crucial components of text-to-image (T2I) generation systems where they are used at various stages for dataset filtering, as evaluation metrics, as a supervisory signal during optimization of parameters, and for post-generation safety and quality filtering of T2I outputs. While specific problems with the integration of RMs into the T2I pipeline have been studied (e.g. reward hacking or mode collapse), their robustness and fairness as scoring functions remains largely unknown. We conduct a large scale audit of RM robustness with respect to demographic biases during T2I model training and generation. We provide quantitative and qualitative evidence that while originally developed as quality measures, RMs encode demographic biases, which cause reward-guided optimization to disproportionately sexualize female image subjects reinforce gender/racial stereotypes, and collapse demographic diversity. These findings highlight shortcomings in current reward models, challenge their reliability as quality metrics, and underscore the need for improved data collection and training procedures to enable more robust scoring.

cs.CV↗

arXiv2026

When Visuals Aren't the Problem: Evaluating Vision-Language Models on Misleading Data Visualizations

Visualizations help communicate data insights, but deceptive data representations can distort their interpretation and propagate misinformation. While recent Vision Language Models (VLMs) perform well on many chart understanding tasks, their ability to detect misleading visualizations, especially when deception arises from subtle reasoning errors in captions, remains poorly understood. Here, we evaluate VLMs on misleading visualization-caption pairs grounded in a fine-grained taxonomy of reasoning errors (e.g., Cherry-picking, Causal inference) and visualization design errors (e.g., Truncated axis, Dual axis, inappropriate encodings). To this end, we develop a benchmark that combines real-world visualization with human-authored, curated misleading captions designed to elicit specific reasoning and visualization error types, enabling controlled analysis across error categories and modalities of misleadingness. Evaluating many commercial and open-source VLMs, we find that models detect visual design errors substantially more reliably than reasoning-based misinformation, and frequently misclassify non-misleading visualizations as deceptive. Overall, our work fills a gap between coarse detection of misleading content and the attribution of the specific reasoning or visualization errors that give rise to it.

cs.CV↗

arXiv2024

Understanding Graphical Perception in Data Visualization through Zero-shot Prompting of Vision-Language Models

Vision Language Models (VLMs) have been successful at many chart comprehension tasks that require attending to both the images of charts and their accompanying textual descriptions. However, it is not well established how VLM performance profiles map to human-like behaviors. If VLMs can be shown to have human-like chart comprehension abilities, they can then be applied to a broader range of tasks, such as designing and evaluating visualizations for human readers. This paper lays the foundations for such applications by evaluating the accuracy of zero-shot prompting of VLMs on graphical perception tasks with established human performance profiles. Our findings reveal that VLMs perform similarly to humans under specific task and style combinations, suggesting that they have the potential to be used for modeling human performance. Additionally, variations to the input stimuli show that VLM accuracy is sensitive to stylistic changes such as fill color and chart contiguity, even when the underlying data and data mappings are the same.

cs.AI↗

arXiv2024

Is What You Ask For What You Get? Investigating Concept Associations in Text-to-Image Models

Text-to-image (T2I) models are increasingly used in impactful real-life applications. As such, there is a growing need to audit these models to ensure that they generate desirable, task-appropriate images. However, systematically inspecting the associations between prompts and generated content in a human-understandable way remains challenging. To address this, we propose Concept2Concept, a framework where we characterize conditional distributions of vision language models using interpretable concepts and metrics that can be defined in terms of these concepts. This characterization allows us to use our framework to audit models and prompt-datasets. To demonstrate, we investigate several case studies of conditional distributions of prompts, such as user-defined distributions or empirical, real-world distributions. Lastly, we implement Concept2Concept as an open-source interactive visualization tool to facilitate use by non-technical end-users. A demo is available at https://tinyurl.com/Concept2ConceptDemo.

cs.CV↗

arXiv2024

MiMICRI: Towards Domain-centered Counterfactual Explanations of Cardiovascular Image Classification Models

The recent prevalence of publicly accessible, large medical imaging datasets has led to a proliferation of artificial intelligence (AI) models for cardiovascular image classification and analysis. At the same time, the potentially significant impacts of these models have motivated the development of a range of explainable AI (XAI) methods that aim to explain model predictions given certain image inputs. However, many of these methods are not developed or evaluated with domain experts, and explanations are not contextualized in terms of medical expertise or domain knowledge. In this paper, we propose a novel framework and python library, MiMICRI, that provides domain-centered counterfactual explanations of cardiovascular image classification models. MiMICRI helps users interactively select and replace segments of medical images that correspond to morphological structures. From the counterfactuals generated, users can then assess the influence of each segment on model predictions, and validate the model against known medical facts. We evaluate this library with two medical experts. Our evaluation demonstrates that a domain-centered XAI approach can enhance the interpretability of model explanations, and help experts reason about models in terms of relevant domain knowledge. However, concerns were also surfaced about the clinical plausibility of the counterfactuals generated. We conclude with a discussion on the generalizability and trustworthiness of the MiMICRI framework, as well as the implications of our findings on the development of domain-centered XAI methods for model interpretability in healthcare contexts.

cs.HC↗

arXiv2024

What We Augment When We Augment Visualizations: A Design Elicitation Study of How We Visually Express Data Relationships

Visual augmentations are commonly added to charts and graphs in order to convey richer and more nuanced information about relationships in the data. However, many design spaces proposed for categorizing augmentations were defined in a top-down manner, based on expert heuristics or from surveys of published visualizations. Less well understood are user preferences and intuitions when designing augmentations. In this paper, we address the gap by conducting a design elicitation study, where study participants were asked to draw the different ways they would visually express the meaning of ten different prompts. We obtained 364 drawings from the study, and identified the emergent categories of augmentations used by participants. The contributions of this paper are: (i) a user-defined design space of visualization augmentations, (ii) a repository of hand drawn augmentations made by study participants, and (iii) a discussion of insights into participant considerations, and connections between our study and existing design guidelines.

cs.HC↗

arXiv2024

Visualizing Intelligent Tutor Interactions for Responsive Pedagogy

Intelligent tutoring systems leverage AI models of expert learning and student knowledge to deliver personalized tutoring to students. While these intelligent tutors have demonstrated improved student learning outcomes, it is still unclear how teachers might integrate them into curriculum and course planning to support responsive pedagogy. In this paper, we conducted a design study with five teachers who have deployed Apprentice Tutors, an intelligent tutoring platform, in their classes. We characterized their challenges around analyzing student interaction data from intelligent tutoring systems and built VisTA (Visualizations for Tutor Analytics), a visual analytics system that shows detailed provenance data across multiple coordinated views. We evaluated VisTA with the same five teachers, and found that the visualizations helped them better interpret intelligent tutor data, gain insights into student problem-solving provenance, and decide on necessary follow-up actions - such as providing students with further support or reviewing skills in the classroom. Finally, we discuss potential extensions of VisTA into sequence query and detection, as well as the potential for the visualizations to be useful for encouraging self-directed learning in students.

cs.HC↗

arXiv2024

Explainability in JupyterLab and Beyond: Interactive XAI Systems for Integrated and Collaborative Workflows

Explainable AI (XAI) tools represent a turn to more human-centered and human-in-the-loop AI approaches that emphasize user needs and perspectives in machine learning model development workflows. However, while the majority of ML resources available today are developed for Python computational environments such as JupyterLab and Jupyter Notebook, the same has not been true of interactive XAI systems, which are often still implemented as standalone interfaces. In this paper, we address this mismatch by identifying three design patterns for embedding front-end XAI interfaces into Jupyter, namely: 1) One-way communication from Python to JavaScript, 2) Two-way data synchronization, and 3) Bi-directional callbacks. We also provide an open-source toolkit, bonXAI, that demonstrates how each design pattern might be used to build interactive XAI tools for a Pytorch text classification workflow. Finally, we conclude with a discussion of best practices and open questions. Our aims for this paper are to discuss how interactive XAI tools might be developed for computational notebooks, and how they can better integrate into existing model development workflows to support more collaborative, human-centered AI.

cs.HC↗

arXiv2024

Situating Data Sets: Making Public Data Actionable for Housing Justice

Activists, governmentsm and academics regularly advocate for more open data. But how is data made open, and for whom is it made useful and usable? In this paper, we investigate and describe the work of making eviction data open to tenant organizers. We do this through an ethnographic description of ongoing work with a local housing activist organization. This work combines observation, direct participation in data work, and creating media artifacts, specifically digital maps. Our interpretation is grounded in D'Ignazio and Klein's Data Feminism, emphasizing standpoint theory. Through our analysis and discussion, we highlight how shifting positionalities from data intermediaries to data accomplices affects the design of data sets and maps. We provide HCI scholars with three design implications when situating data for grassroots organizers: becoming a domain beginner, striving for data actionability, and evaluating our design artifacts by the social relations they sustain rather than just their technical efficacy.

cs.HC↗

arXiv2023

Causalvis: Visualizations for Causal Inference

Causal inference is a statistical paradigm for quantifying causal effects using observational data. It is a complex process, requiring multiple steps, iterations, and collaborations with domain experts. Analysts often rely on visualizations to evaluate the accuracy of each step. However, existing visualization toolkits are not designed to support the entire causal inference process within computational environments familiar to analysts. In this paper, we address this gap with Causalvis, a Python visualization package for causal inference. Working closely with causal inference experts, we adopted an iterative design process to develop four interactive visualization modules to support causal inference analysis tasks. The modules are then presented back to the experts for feedback and evaluation. We found that Causalvis effectively supported the iterative causal inference process. We discuss the implications of our findings for designing visualizations for causal inference, particularly for tasks of communication and collaboration.

cs.HC↗

arXiv2021

VAINE: Visualization and AI for Natural Experiments

Natural experiments are observational studies where the assignment of treatment conditions to different populations occurs by chance "in the wild". Researchers from fields such as economics, healthcare, and the social sciences leverage natural experiments to conduct hypothesis testing and causal effect estimation for treatment and outcome variables that would otherwise be costly, infeasible, or unethical. In this paper, we introduce VAINE (Visualization and AI for Natural Experiments), a visual analytics tool for identifying and understanding natural experiments from observational data. We then demonstrate how VAINE can be used to validate causal relationships, estimate average treatment effects, and identify statistical phenomena such as Simpson's paradox through two usage scenarios.

cs.HC↗

arXiv2020

A Comparative Analysis of Industry Human-AI Interaction Guidelines

With the recent release of AI interaction guidelines from Apple, Google, and Microsoft, there is clearly interest in understanding the best practices in human-AI interaction. However, industry standards are not determined by a single company, but rather by the synthesis of knowledge from the whole community. We have surveyed all of the design guidelines from each of these major companies and developed a single, unified structure of guidelines, giving developers a centralized reference. We have then used this framework to compare each of the surveyed companies to find differences in areas of emphasis. Finally, we encourage people to contribute additional guidelines from other companies, academia, or individuals, to provide an open and extensible reference of AI design guidelines at https://ai-open-guidelines.readthedocs.io/.

cs.HC↗

arXiv2020

Should We Trust (X)AI? Design Dimensions for Structured Experimental Evaluations

This paper systematically derives design dimensions for the structured evaluation of explainable artificial intelligence (XAI) approaches. These dimensions enable a descriptive characterization, facilitating comparisons between different study designs. They further structure the design space of XAI, converging towards a precise terminology required for a rigorous study of XAI. Our literature review differentiates between comparative studies and application papers, revealing methodological differences between the fields of machine learning, human-computer interaction, and visual analytics. Generally, each of these disciplines targets specific parts of the XAI process. Bridging the resulting gaps enables a holistic evaluation of XAI in real-world scenarios, as proposed by our conceptual model characterizing bias sources and trust-building. Furthermore, we identify and discuss the potential for future work based on observed research gaps that should lead to better coverage of the proposed model.

cs.HC↗