arXiv subjects

Eunyee Koh

Publications and source records attributed to Eunyee Koh.

At least 19 recordsLinked to original sources

arXiv2026

AnnoSketch: Evaluating and Collecting Human Sketches for MLLM-assisted Chart Annotation

As multimodal large language models (MLLMs) support a growing range of input modalities, increasing work explores how to incorporate rough sketches to convey user intent. For annotated chart generation, it remains unclear what annotation sketches people provide and when such visual input helps MLLMs generate more useful annotations. In this study, we examine when sketch input is useful for MLLM-generated chart annotations across variation in chart type and caption type. In addition, we qualitatively analyze participants' explanations of their output preferences to characterize what made generated annotations more or less helpful. To further document participants' annotation sketches, we present AnnoSketch, comprising 1,600 annotation sketches collected across 160 chart-caption pairs from the conditions in which sketch guidance proved most beneficial, together with participants' annotation intents, perceived comprehension difficulty, and self-reported expressive limitations. We also label these sketches with structured metadata describing how each sketch relates to its caption and how participants express annotations through visual marks. Together, our study and AnnoSketch help determine when to solicit sketch input and provide empirical source for how people sketch chart annotations to support captions. The dataset and supplemental materials are available in our OSF repository.

cs.HC↗

arXiv2026

Surprise2Refine: Axis-Centered Exploration-To-Refinement for Agent-Assisted Creative Scaffolding

Designers require different design spaces across creative stages: broad during exploration, and targeted during refinement. Yet existing agent-driven tools assume a fixed or continuously expanding space, leaving designers to manage and navigate it themselves. Informed by a formative study with five designers, we propose an axis-centered workflow that adaptively broadens and narrows the design space to support structured exploration and refinement. We implemented this workflow in Surprise2Refine, a prototype that allows users to build and reshape an nxn design space through a set of axis-centered interactions as their creative intent evolves. A within-subjects study with 14 designers shows that Surprise2Refine enhances users' sense of control, supports tracking of scaffolding paths, and improves the perceived creativity of design outcomes. We further distill design insights to guide future agent-assisted tools for creative scaffolding.

cs.HC↗

arXiv2026

UXCascade: Scalable Usability Testing with Simulated User Agents

Simulated user agents are increasingly deployed in usability testing to support fast, iterative UX workflows, as they generate rich data such as action logs and think-aloud reasoning, but the unstructured nature of this output often obscures actionable insights. We present UXCascade, an interactive tool for extracting, aggregating, and presenting agent-generated usability feedback at scale. Our core contribution is a multi-level analysis workflow that (1) highlights patterns across persona traits, goals, and outcomes, (2) links agent reasoning to specific issues, and (3) supports actionable design improvements. UXCascade operationalizes this approach by listing agent goals, traits, and issues in a structured overview. Practitioners can explore detailed reasoning traces and annotated views, propose interface edits, and assess their impact across personas. This enables a top-down, exploration-driven analysis from patterns to concrete, actionable UX interventions. A user study with eight UX professionals demonstrates that UXCascade integrates into existing workflows, enabling iterative feedback during early-stage interface development.

cs.HC↗

arXiv2026

Narrix: Remixing Narrative Strategies from Examples for Story Writing

Experienced storytellers decompose stories into local narrative strategies and how these strategies shape higher-level arcs. This decomposition helps writers recognize patterns in others' work and adapt those patterns to tell new stories. Novices, however, struggle to identify these strategies or to reuse them effectively. We present Narrix, a novel writing tool that helps novice writers recognize narrative strategies in example stories and repurpose these strategies in their own writing. Narrix analyzes strategies in example stories, highlights them with color-coded lexical cues and explanations, and situates them on an interactive story arc for exploration by emotional shifts and turning points. Writers then drag strategies onto multi-dimensional tracks and apply block-scoped edits to revise or continue their drafts through controlled generation steered by specified strategies. Through a within-subjects study (N=12), Narrix showed improved participants' retention, confidence, and creative adaptation of narrative strategies compared to a baseline chat-based writing interface.

cs.HC↗

arXiv2026

XAgen: An Explainability Tool for Identifying and Correcting Failures in Multi-Agent Workflows

As multi-agent systems powered by Large Language Models (LLMs) are increasingly adopted in real-world workflows, users with diverse technical backgrounds are now building and refining their own agentic processes. However, these systems can fail in opaque ways, making it difficult for users to observe, understand, and correct errors. We conducted formative interviews with 12 practitioners to identify mismatches between existing debugging tools and users' needs. Based on these insights, we designed XAgen, an explainability tool that supports users with varying AI expertise through three core capabilities: log visualization for glanceable workflow understanding, human-in-the-loop feedback to capture expert judgment, and automatic error detection via an LLM-as-a-judge. In a user study with 8 participants, XAgen helped users locate failures more easily, attribute to specific agents or steps, and iteratively improve configurations. Our findings surface human-centered design guidelines for explainable agentic AI development and highlight opportunities for more context-aware interactive debugging.

cs.HC↗

arXiv2025

OnGoal: Tracking and Visualizing Conversational Goals in Multi-Turn Dialogue with Large Language Models

As multi-turn dialogues with large language models (LLMs) grow longer and more complex, how can users better evaluate and review progress on their conversational goals? We present OnGoal, an LLM chat interface that helps users better manage goal progress. OnGoal provides real-time feedback on goal alignment through LLM-assisted evaluation, explanations for evaluation results with examples, and overviews of goal progression over time, enabling users to navigate complex dialogues more effectively. Through a study with 20 participants on a writing task, we evaluate OnGoal against a baseline chat interface without goal tracking. Using OnGoal, participants spent less time and effort to achieve their goals while exploring new prompting strategies to overcome miscommunication, suggesting tracking and visualizing goals can enhance engagement and resilience in LLM dialogues. Our findings inspired design implications for future LLM chat interfaces that improve goal communication, reduce cognitive load, enhance interactivity, and enable feedback to improve LLM performance.

cs.HC↗

arXiv2025

Chart-to-Experience: Benchmarking Multimodal LLMs for Predicting Experiential Impact of Charts

The field of Multimodal Large Language Models (MLLMs) has made remarkable progress in visual understanding tasks, presenting a vast opportunity to predict the perceptual and emotional impact of charts. However, it also raises concerns, as many applications of LLMs are based on overgeneralized assumptions from a few examples, lacking sufficient validation of their performance and effectiveness. We introduce Chart-to-Experience, a benchmark dataset comprising 36 charts, evaluated by crowdsourced workers for their impact on seven experiential factors. Using the dataset as ground truth, we evaluated capabilities of state-of-the-art MLLMs on two tasks: direct prediction and pairwise comparison of charts. Our findings imply that MLLMs are not as sensitive as human evaluators when assessing individual charts, but are accurate and reliable in pairwise comparisons.

cs.HC↗

arXiv2025

Utilizing Provenance as an Attribute for Visual Data Analysis: A Design Probe with ProvenanceLens

Analytic provenance can be visually encoded to help users track their ongoing analysis trajectories, recall past interactions, and inform new analytic directions. Despite its significance, provenance is often hardwired into analytics systems, affording limited user control and opportunities for self-reflection. We thus propose modeling provenance as an attribute that is available to users during analysis. We demonstrate this concept by modeling two provenance attributes that track the recency and frequency of user interactions with data. We integrate these attributes into a visual data analysis system prototype, ProvenanceLens, wherein users can visualize their interaction recency and frequency by mapping them to encoding channels (e.g., color, size) or applying data transformations (e.g., filter, sort). Using ProvenanceLens as a design probe, we conduct an exploratory study with sixteen users to investigate how these provenance-tracking affordances are utilized for both decision-making and self-reflection. We find that users can accurately and confidently answer questions about their analysis, and we show that mismatches between the user's mental model and the provenance encodings can be surprising, thereby prompting useful self-reflection. We also report on the user strategies surrounding these affordances, and reflect on their intuitiveness and effectiveness in representing provenance.

cs.HC↗

arXiv2025

Understanding the Impact of Spatial Immersion in Web Data Stories

An increasing number of web articles engage the reader with the feeling of being immersed in the data space. However, the exact characteristics of spatial immersion in the context of visual storytelling remain vague. For example, what are the common design patterns of data stories with spatial immersion? How do they affect the reader's experience? To gain a deeper understanding of the subject, we collected 23 distinct data stories with spatial immersion, and identified six design patterns, such as cinematic camera shots and transitions, intuitive data representations, realism, naturally moving elements, direct manipulation of camera or visualization, and dynamic dimension. Subsequently, we designed four data stories and conducted a crowdsourced user study comparing three design variations (static, animated, and immersive). Our results suggest that data stories with the design patterns for spatial immersion are more interesting and persuasive than static or animated ones, but no single condition was deemed more understandable or trustworthy.

cs.HC↗

arXiv2025

Detecting Ambiguities to Guide Query Rewrite for Robust Conversations in Enterprise AI Assistants

Multi-turn conversations with an Enterprise AI Assistant can be challenging due to conversational dependencies in questions, leading to ambiguities and errors. To address this, we propose an NLU-NLG framework for ambiguity detection and resolution through reformulating query automatically and introduce a new task called "Ambiguity-guided Query Rewrite." To detect ambiguities, we develop a taxonomy based on real user conversational logs and draw insights from it to design rules and extract features for a classifier which yields superior performance in detecting ambiguous queries, outperforming LLM-based baselines. Furthermore, coupling the query rewrite module with our ambiguity detecting classifier shows that this end-to-end framework can effectively mitigate ambiguities without risking unnecessary insertions of unwanted phrases for clear queries, leading to an improvement in the overall performance of the AI Assistant. Due to its significance, this has been deployed in the real world application, namely Adobe Experience Platform AI Assistant.

cs.CL↗

arXiv2025

Representing Visualization Insights as a Dense Insight Network

We propose a dense insight network framework to encode the relationships between automatically generated insights from a complex dashboard based on their shared characteristics. Our insight network framework includes five high-level categories of relationships (e.g., type, topic, value, metadata, and compound scores). The goal of this insight network framework is to provide a foundation for implementing new insight interpretation and exploration strategies, including both user-driven and automated approaches. To illustrate the complexity and flexibility of our framework, we first describe a visualization playground to directly visualize key network characteristics; this playground also demonstrates potential interactive capabilities for decomposing the dense insight network. Then, we discuss a case study application for ranking insights based on the underlying network characteristics captured by our framework, before prompting a large language model to generate a concise, natural language summary. Finally, we reflect on next steps for leveraging our insight network framework to design and evaluate new systems.

cs.HC↗

arXiv2024

SonifyAR: Context-Aware Sound Generation in Augmented Reality

Sound plays a crucial role in enhancing user experience and immersiveness in Augmented Reality (AR). However, current platforms lack support for AR sound authoring due to limited interaction types, challenges in collecting and specifying context information, and difficulty in acquiring matching sound assets. We present SonifyAR, an LLM-based AR sound authoring system that generates context-aware sound effects for AR experiences. SonifyAR expands the current design space of AR sound and implements a Programming by Demonstration (PbD) pipeline to automatically collect contextual information of AR events, including virtual content semantics and real world context. This context information is then processed by a large language model to acquire sound effects with Recommendation, Retrieval, Generation, and Transfer methods. To evaluate the usability and performance of our system, we conducted a user study with eight participants and created five example applications, including an AR-based science experiment, an improving case for AR headset safety, and an assisting example for low vision AR users.

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

WHATSNEXT: Guidance-enriched Exploratory Data Analysis with Interactive, Low-Code Notebooks

Computational notebooks such as Jupyter are popular for exploratory data analysis and insight finding. Despite the module-based structure, notebooks visually appear as a single thread of interleaved cells containing text, code, visualizations, and tables, which can be unorganized and obscure users' data analysis workflow. Furthermore, users with limited coding expertise may struggle to quickly engage in the analysis process. In this work, we design and implement an interactive notebook framework, WHATSNEXT, with the goal of supporting low-code visual data exploration with insight-based user guidance. In particular, we (1) re-design a standard notebook cell to include a recommendation panel that suggests possible next-step exploration questions or analysis actions to take, and (2) create an interactive, dynamic tree visualization that reflects the analytic dependencies between notebook cells to make it easy for users to see the structure of the data exploration threads and trace back to previous steps.

cs.HC↗

arXiv2023

Summaries as Captions: Generating Figure Captions for Scientific Documents with Automated Text Summarization

Good figure captions help paper readers understand complex scientific figures. Unfortunately, even published papers often have poorly written captions. Automatic caption generation could aid paper writers by providing good starting captions that can be refined for better quality. Prior work often treated figure caption generation as a vision-to-language task. In this paper, we show that it can be more effectively tackled as a text summarization task in scientific documents. We fine-tuned PEGASUS, a pre-trained abstractive summarization model, to specifically summarize figure-referencing paragraphs (e.g., "Figure 3 shows...") into figure captions. Experiments on large-scale arXiv figures show that our method outperforms prior vision methods in both automatic and human evaluations. We further conducted an in-depth investigation focused on two key challenges: (i) the common presence of low-quality author-written captions and (ii) the lack of clear standards for good captions. Our code and data are available at: https://github.com/Crowd-AI-Lab/Generating-Figure-Captions-as-a-Text-Summarization-Task.

cs.CL↗

arXiv2023

CGC: Contrastive Graph Clustering for Community Detection and Tracking

Given entities and their interactions in the web data, which may have occurred at different time, how can we find communities of entities and track their evolution? In this paper, we approach this important task from graph clustering perspective. Recently, state-of-the-art clustering performance in various domains has been achieved by deep clustering methods. Especially, deep graph clustering (DGC) methods have successfully extended deep clustering to graph-structured data by learning node representations and cluster assignments in a joint optimization framework. Despite some differences in modeling choices (e.g., encoder architectures), existing DGC methods are mainly based on autoencoders and use the same clustering objective with relatively minor adaptations. Also, while many real-world graphs are dynamic, previous DGC methods considered only static graphs. In this work, we develop CGC, a novel end-to-end framework for graph clustering, which fundamentally differs from existing methods. CGC learns node embeddings and cluster assignments in a contrastive graph learning framework, where positive and negative samples are carefully selected in a multi-level scheme such that they reflect hierarchical community structures and network homophily. Also, we extend CGC for time-evolving data, where temporal graph clustering is performed in an incremental learning fashion, with the ability to detect change points. Extensive evaluation on real-world graphs demonstrates that the proposed CGC consistently outperforms existing methods.

cs.SI↗

arXiv2023

DataPilot: Utilizing Quality and Usage Information for Subset Selection during Visual Data Preparation

Selecting relevant data subsets from large, unfamiliar datasets can be difficult. We address this challenge by modeling and visualizing two kinds of auxiliary information: (1) quality - the validity and appropriateness of data required to perform certain analytical tasks; and (2) usage - the historical utilization characteristics of data across multiple users. Through a design study with 14 data workers, we integrate this information into a visual data preparation and analysis tool, DataPilot. DataPilot presents visual cues about "the good, the bad, and the ugly" aspects of data and provides graphical user interface controls as interaction affordances, guiding users to perform subset selection. Through a study with 36 participants, we investigate how DataPilot helps users navigate a large, unfamiliar tabular dataset, prepare a relevant subset, and build a visualization dashboard. We find that users selected smaller, effective subsets with higher quality and usage, and with greater success and confidence.

cs.HC↗

arXiv2022

PersonaSAGE: A Multi-Persona Graph Neural Network

Graph Neural Networks (GNNs) have become increasingly important in recent years due to their state-of-the-art performance on many important downstream applications. Existing GNNs have mostly focused on learning a single node representation, despite that a node often exhibits polysemous behavior in different contexts. In this work, we develop a persona-based graph neural network framework called PersonaSAGE that learns multiple persona-based embeddings for each node in the graph. Such disentangled representations are more interpretable and useful than a single embedding. Furthermore, PersonaSAGE learns the appropriate set of persona embeddings for each node in the graph, and every node can have a different number of assigned persona embeddings. The framework is flexible enough and the general design helps in the wide applicability of the learned embeddings to suit the domain. We utilize publicly available benchmark datasets to evaluate our approach and against a variety of baselines. The experiments demonstrate the effectiveness of PersonaSAGE for a variety of important tasks including link prediction where we achieve an average gain of 15% while remaining competitive for node classification. Finally, we also demonstrate the utility of PersonaSAGE with a case study for personalized recommendation of different entity types in a data management platform.

cs.LG↗