arXiv subjects

Jeffrey Heer

Publications and source records attributed to Jeffrey Heer.

At least 19 recordsLinked to original sources

arXiv2026

ShellVis: Sandboxed Live Programming for Shell Scripts

Live programming provides visibility to programmers by running and tracing programs as they are edited. However, for programs with potentially harmful side effects, liveness can turn mistakes into disasters. We propose enabling live programming in environments with side effects via sandboxing: confining effects to a simulation of the true environment. We apply sandboxed live programming in the challenging context of shell scripting: a ubiquitous and powerful---yet notoriously opaque and error-prone---tool. ShellVis provides line-by-line feedback on a shell script's run-time behavior, with file operations sandboxed via a safe overlay of the file system. A qualitative user evaluation finds ShellVis to be helpful to participants, replacing tedious existing practices and instilling confidence. Participant responses also reveal areas for future research, particularly bridging the gulf of execution alongside the gulf of evaluation. ShellVis serves as a case study of how sandboxing can bring live-programming techniques into the many real-world programming contexts where side effects are important.

cs.HC↗

arXiv2026

How Do Researchers Manage Visualization Experiment Stimuli?

Visualization experiments need a set of "good" stimuli that effectively address research questions and hypotheses. Creating, managing, and deploying stimuli are often challenging, as these tasks require tremendous care. Inappropriate stimuli can make the outcome invalid or uninteresting, wasting both researchers' and participants' resources. As the speed of science increases, better support for stimuli-related tasks is essential, yet we lack a closer look at how visualization researchers deal with them. To understand the experiences of visualization experimenters and guide future improvements, we interviewed 19 visualization researchers with diverse backgrounds and experiences. Our findings describe practices and challenges across the life cycle of stimuli, from exploration and selection through shipment, deployment, and analysis. For example, stimuli management and deployment require tedious manual effort, which does not scale for experiments with many levels and complex conditioning. We also discuss both concerns and optimism around AI-assisted visualization experiment design. We conclude with future research opportunities in supporting stimuli creation, automated stimuli inspection, and experimental apparatus concerns.

cs.HC↗

arXiv2026

GeoVisA11y: An AI-based Geovisualization Question-Answering System for Screen-Reader Users

Geovisualizations are powerful tools for communicating spatial information, but are inaccessible to screen-reader users. To address this limitation, we present GeoVisA11y, an LLM-based question-answering system that makes geovisualizations accessible through natural language interaction. The system supports map reading, analysis, interpretation and navigation by handling analytical, geospatial, visual and contextual queries. Through user studies with 12 screen-reader users and sighted participants, we demonstrate that GeoVisA11y effectively bridges accessibility gaps while revealing distinct interaction patterns between user groups. We contribute: (1) an open-source, accessible geovisualization system, (2) empirical findings on query and navigation differences, and (3) a dataset of geospatial queries to inform future research on accessible data visualization.

cs.HC↗

arXiv2026

Automatic Synthesis of Visualization Design Knowledge Bases

Formal representations of the visualization design space, such as knowledge bases and graphs, consolidate design practices into a shared resource and enable automated reasoning and interpretable design recommendations. However, prior approaches typically depend on fixed, manually authored rules, making it difficult to build novel representations or extend them for different visualization domains. Instead, we propose data-driven methods that automatically synthesize visualization design knowledge bases. Specifically, our methods (1) extract candidate design features from a visualization corpus, (2) select features forward and backward, and (3) render the final knowledge base. In our benchmark evaluation compared to Draco 2, our synthesized knowledge base offers general and interpretable design features and improves the accuracy of predicting effective designs by 1-15% in varied training and test sets. When we apply our approach to genomics visualization, the synthesized knowledge base includes sensible features with accuracy up to 97%, demonstrating the applicability of our approach to other visualization domains.

cs.HC↗

arXiv2025

Just-In-Time Objectives: A General Approach for Specialized AI Interactions

Large language models promise a broad set of functions, but when not given a specific objective, they default to generic results. We demonstrate that inferring the user's in-the-moment objective, then rapidly optimizing for that singular objective, enables LLMs to produce specialized tools, interfaces, and responses. Our work introduces just-in-time objectives, which model a user's goals to specialize LLM systems on the fly. We contribute an architecture for automatically inducing such objectives by passively observing user behavior, then steering downstream AI systems through generation and evaluation against this objective. Inducing just-in-time objectives (e.g., "Clarify the abstract's research contribution") enables automatic generation of tools, e.g., those that critique a draft based on relevant HCI methodologies, anticipate related researchers' reactions, or surface ambiguous terminology. In a series of experiments on participants' own tasks, JIT objectives enable LLM outputs that achieve 66-86% win rates over typical LLMs. In-person use sessions confirm that JIT objectives produce specialized tools that are unique to each participant and are rated as significantly higher quality than a standard LLM chat tool.

cs.HC↗

arXiv2025

Data Augmentation for Visualization Design Knowledge Bases

Visualization knowledge bases enable computational reasoning and recommendation over a visualization design space. These systems evaluate design trade-offs using numeric weights assigned to different features (e.g., binning a variable). Feature weights can be learned automatically by fitting a model to a collection of chart pairs, in which one chart is deemed preferable to the other. To date, labeled chart pairs have been drawn from published empirical research results; however, such pairs are not comprehensive, resulting in a training corpus that lacks many design variants and fails to systematically assess potential trade-offs. To improve knowledge base coverage and accuracy, we contribute data augmentation techniques for generating and labeling chart pairs. We present methods to generate novel chart pairs based on design permutations and by identifying under-assessed features -- leading to an expanded corpus with thousands of new chart pairs, now in need of labels. Accordingly, we next compare varied methods to scale labeling efforts to annotate chart pairs, in order to learn updated feature weights. We evaluate our methods in the context of the Draco knowledge base, demonstrating improvements to both feature coverage and chart recommendation performance.

cs.HC↗

arXiv2025

Mosaic Selections: Managing and Optimizing User Selections for Scalable Data Visualization Systems

Though powerful tools for analysis and communication, interactive visualizations often fail to support real-time interaction with large datasets with millions or more records. To highlight and filter data, users indicate values or intervals of interest. Such selections may span multiple components, combine in complex ways, and require optimizations to ensure low-latency updates. We describe Mosaic Selections, a model for representing, managing, and optimizing user selections, in which one or more filter predicates are added to queries that request data for visualizations and input widgets. By analyzing both queries and selection predicates, Mosaic Selections enable automatic optimizations, including pre-aggregating data to rapidly compute selection updates. We contribute a formal description of our selection model and optimization methods, and their implementation in the open-source Mosaic architecture. Benchmark results demonstrate orders-of-magnitude latency improvements for selection-based optimizations over unoptimized queries and existing optimizers for the Vega language. The Mosaic Selection model provides infrastructure for flexible, interoperable filtering across multiple visualizations, alongside automatic optimizations to scale to millions and even billions of records.

cs.HC↗

arXiv2025

Interactive Reasoning: Visualizing and Controlling Chain-of-Thought Reasoning in Large Language Models

The output quality of large language models (LLMs) can be improved via "reasoning": generating segments of chain-of-thought (CoT) content to further condition the model prior to producing user-facing output. While these chains contain valuable information, they are verbose and lack explicit organization, making them tedious to review. Moreover, they lack opportunities for user feedback, such as to remove unwanted considerations, add desired ones, or clarify unclear assumptions. We introduce Interactive Reasoning, an interaction design that visualizes chain-of-thought outputs as a hierarchy of topics and enables user review and modification. We implement interactive reasoning in Hippo, a prototype for AI-assisted decision making in the face of uncertain trade-offs. In a user study with 16 participants, we find that interactive reasoning in Hippo allows users to quickly identify and interrupt erroneous generations, efficiently steer the model towards customized responses, and better understand both model reasoning and model outputs. Our work contributes to a new paradigm that incorporates user oversight into LLM reasoning processes.

cs.HC↗

arXiv2024

From Pen to Prompt: How Creative Writers Integrate AI into their Writing Practice

Creative writing is a deeply human craft, yet AI systems using large language models (LLMs) offer the automation of significant parts of the writing process. So why do some creative writers choose to use AI? Through interviews and observed writing sessions with 18 creative writers who already use AI regularly in their writing practice, we find that creative writers are intentional about how they incorporate AI, making many deliberate decisions about when and how to engage AI based on their core values, such as authenticity and craftsmanship. We characterize the interplay between writers' values, their fluid relationships with AI, and specific integration strategies -- ultimately enabling writers to create new AI workflows without compromising their creative values. We provide insight for writing communities, AI developers and future researchers on the importance of supporting transparency of these emerging writing processes and rethinking what AI features can best serve writers.

cs.HC↗

arXiv2024

BLADE: Benchmarking Language Model Agents for Data-Driven Science

Data-driven scientific discovery requires the iterative integration of scientific domain knowledge, statistical expertise, and an understanding of data semantics to make nuanced analytical decisions, e.g., about which variables, transformations, and statistical models to consider. LM-based agents equipped with planning, memory, and code execution capabilities have the potential to support data-driven science. However, evaluating agents on such open-ended tasks is challenging due to multiple valid approaches, partially correct steps, and different ways to express the same decisions. To address these challenges, we present BLADE, a benchmark to automatically evaluate agents' multifaceted approaches to open-ended research questions. BLADE consists of 12 datasets and research questions drawn from existing scientific literature, with ground truth collected from independent analyses by expert data scientists and researchers. To automatically evaluate agent responses, we developed corresponding computational methods to match different representations of analyses to this ground truth. Though language models possess considerable world knowledge, our evaluation shows that they are often limited to basic analyses. However, agents capable of interacting with the underlying data demonstrate improved, but still non-optimal, diversity in their analytical decision making. Our work enables the evaluation of agents for data-driven science and provides researchers deeper insights into agents' analysis approaches.

cs.CL↗

arXiv2024

DracoGPT: Extracting Visualization Design Preferences from Large Language Models

Trained on vast corpora, Large Language Models (LLMs) have the potential to encode visualization design knowledge and best practices. However, if they fail to do so, they might provide unreliable visualization recommendations. What visualization design preferences, then, have LLMs learned? We contribute DracoGPT, a method for extracting, modeling, and assessing visualization design preferences from LLMs. To assess varied tasks, we develop two pipelines--DracoGPT-Rank and DracoGPT-Recommend--to model LLMs prompted to either rank or recommend visual encoding specifications. We use Draco as a shared knowledge base in which to represent LLM design preferences and compare them to best practices from empirical research. We demonstrate that DracoGPT can accurately model the preferences expressed by LLMs, enabling analysis in terms of Draco design constraints. Across a suite of backing LLMs, we find that DracoGPT-Rank and DracoGPT-Recommend moderately agree with each other, but both substantially diverge from guidelines drawn from human subjects experiments. Future work can build on our approach to expand Draco's knowledge base to model a richer set of preferences and to provide a robust and cost-effective stand-in for LLMs.

cs.HC↗

arXiv2024

Mixing Linters with GUIs: A Color Palette Design Probe

Visualization linters are end-user facing evaluators that automatically identify potential chart issues. These spell-checker like systems offer a blend of interpretability and customization that is not found in other forms of automated assistance. However, existing linters do not model context and have primarily targeted users who do not need assistance, resulting in obvious -- even annoying -- advice. We investigate these issues within the domain of color palette design, which serves as a microcosm of visualization design concerns. We contribute a GUI-based color palette linter as a design probe that covers perception, accessibility, context, and other design criteria, and use it to explore visual explanations, integrated fixes, and user defined linting rules. Through a formative interview study and theory-driven analysis, we find that linters can be meaningfully integrated into graphical contexts thereby addressing many of their core issues. We discuss implications for integrating linters into visualization tools, developing improved assertion languages, and supporting end-user tunable advice -- all laying the groundwork for more effective visualization linters in any context.

cs.HC↗

arXiv2024

AltGeoViz: Facilitating Accessible Geovisualization

Geovisualizations are powerful tools for exploratory spatial analysis, enabling sighted users to discern patterns, trends, and relationships within geographic data. However, these visual tools have remained largely inaccessible to screen-reader users. We present AltGeoViz, a new system we designed to facilitate geovisualization exploration for these users. AltGeoViz dynamically generates alt-text descriptions based on the user's current map view, providing summaries of spatial patterns and descriptive statistics. In a study of five screen-reader users, we found that AltGeoViz enabled them to interact with geovisualizations in previously infeasible ways. Participants demonstrated a clear understanding of data summaries and their location context, and they could synthesize spatial understandings of their explorations. Moreover, we identified key areas for improvement, such as the addition of intuitive spatial navigation controls and comparative analysis features.

cs.HC↗

arXiv2024

Concept Induction: Analyzing Unstructured Text with High-Level Concepts Using LLooM

Data analysts have long sought to turn unstructured text data into meaningful concepts. Though common, topic modeling and clustering focus on lower-level keywords and require significant interpretative work. We introduce concept induction, a computational process that instead produces high-level concepts, defined by explicit inclusion criteria, from unstructured text. For a dataset of toxic online comments, where a state-of-the-art BERTopic model outputs "women, power, female," concept induction produces high-level concepts such as "Criticism of traditional gender roles" and "Dismissal of women's concerns." We present LLooM, a concept induction algorithm that leverages large language models to iteratively synthesize sampled text and propose human-interpretable concepts of increasing generality. We then instantiate LLooM in a mixed-initiative text analysis tool, enabling analysts to shift their attention from interpreting topics to engaging in theory-driven analysis. Through technical evaluations and four analysis scenarios ranging from literature review to content moderation, we find that LLooM's concepts improve upon the prior art of topic models in terms of quality and data coverage. In expert case studies, LLooM helped researchers to uncover new insights even from familiar datasets, for example by suggesting a previously unnoticed concept of attacks on out-party stances in a political social media dataset.

cs.HC↗

arXiv2024

Interaction Techniques for Exploratory Data Visualization on Mobile Devices

The ubiquity and on-the-go availability of mobile devices makes them central to many tasks such as interpersonal communication and media consumption. However, despite the potential of mobile devices for on-demand exploratory data visualization, existing mobile interactions are difficult, often using highly custom interactions, complex gestures, or multi-modal input. We synthesize limitations from the literature and outline four motivating principles for improved mobile interaction: leverage ubiquitous modalities, prioritize discoverability, enable rapid in-context data exploration, and promote graceful recovery. We then contribute thirteen interaction candidates and conduct a formative study with twelve participants who experienced our interactions in a testbed prototype. Based on these interviews, we discuss design considerations and tradeoffs from four main themes: precise and rapid inspection, focused navigation, single-touch and fixed orientation interaction, and judicious use of motion.

cs.HC↗

arXiv2023

Designing LLM Chains by Adapting Techniques from Crowdsourcing Workflows

LLM chains enable complex tasks by decomposing work into a sequence of subtasks. Similarly, the more established techniques of crowdsourcing workflows decompose complex tasks into smaller tasks for human crowdworkers. Chains address LLM errors analogously to the way crowdsourcing workflows address human error. To characterize opportunities for LLM chaining, we survey 107 papers across the crowdsourcing and chaining literature to construct a design space for chain development. The design space covers a designer's objectives and the tactics used to build workflows. We then surface strategies that mediate how workflows use tactics to achieve objectives. To explore how techniques from crowdsourcing may apply to chaining, we adapt crowdsourcing workflows to implement LLM chains across three case studies: creating a taxonomy, shortening text, and writing a short story. From the design space and our case studies, we identify takeaways for effective chain design and raise implications for future research and development.

cs.HC↗

arXiv2023

DIVI: Dynamically Interactive Visualization

Dynamically Interactive Visualization (DIVI) is a novel approach for orchestrating interactions within and across static visualizations. DIVI deconstructs Scalable Vector Graphics charts at runtime to infer content and coordinate user input, decoupling interaction from specification logic. This decoupling allows interactions to extend and compose freely across different tools, chart types, and analysis goals. DIVI exploits positional relations of marks to detect chart components such as axes and legends, reconstruct scales and view encodings, and infer data fields. DIVI then enumerates candidate transformations across inferred data to perform linking between views. To support dynamic interaction without prior specification, we introduce a taxonomy that formalizes the space of standard interactions by chart element, interaction type, and input event. We demonstrate DIVI's usefulness for rapid data exploration and analysis through a usability study with 13 participants and a diverse gallery of dynamically interactive visualizations, including single chart, multi-view, and cross-tool configurations.

cs.HC↗

arXiv2023

rTisane: Externalizing conceptual models for data analysis increases engagement with domain knowledge and improves statistical model quality

Statistical models should accurately reflect analysts' domain knowledge about variables and their relationships. While recent tools let analysts express these assumptions and use them to produce a resulting statistical model, it remains unclear what analysts want to express and how externalization impacts statistical model quality. This paper addresses these gaps. We first conduct an exploratory study of analysts using a domain-specific language (DSL) to express conceptual models. We observe a preference for detailing how variables relate and a desire to allow, and then later resolve, ambiguity in their conceptual models. We leverage these findings to develop rTisane, a DSL for expressing conceptual models augmented with an interactive disambiguation process. In a controlled evaluation, we find that rTisane's DSL helps analysts engage more deeply with and accurately externalize their assumptions. rTisane also leads to statistical models that match analysts' assumptions, maintain analysis intent, and better fit the data.

cs.HC↗