Qianwen Wang

Jiaju Chen, Yuxuan Lu, Shao Zhang et al.

Interactive story reading is a common parent-child activity, where parents expect to teach both language skills and real-world knowledge beyond the story. While increasing storytelling and reading systems have been developed for this activity, they often fail to infuse real-world knowledge into the conversation. This limitation can be attributed to the existing question-answering (QA) datasets used for children's education, upon which the systems are built, failing to capture the nuances of how education experts think when conducting interactive story reading activities. To bridge this gap, we design an annotation framework, empowered by existing knowledge graph to capture experts' annotations and thinking process, and leverage this framework to construct StorySparkQA dataset, which comprises 5,868 expert-annotated QA pairs with real-world knowledge. We conduct automated and human expert evaluations across various QA pair generation settings to demonstrate that our StorySparkQA can effectively support models in generating QA pairs that target real-world knowledge beyond story content. StorySparkQA is available at https://huggingface.co/datasets/NEU-HAI/StorySparkQA.

Mauricio Villavicencio, Sitong Pan, Qianwen Wang

Despite warnings that LLMs can make mistakes, users often develop inappropriate trust and accept incorrect answers without critical evaluation. Uncertainty quantification (UQ), displaying LLMs' confidence, has emerged as a promising approach to calibrate user trust. However, prior empirical studies on uncertainty communication have treated uncertainty as a single numerical score or simple natural language expression. This simplification fails to capture a key property of LLM outputs: a single response often comprises multiple claims and reasoning steps, each with distinct levels of uncertainty. To address this gap, this study investigates uncertainty granularity (i.e., the extent to which uncertainty is expressed at different levels within an LLM response) and examines its impact on LLM-assisted decision-making. We conducted a large-scale, between-subjects study (N=192) in which participants answered medical questions using LLMs that displayed uncertainty at three different granularities: output-level (entire response), relation-level (individual reasoning steps), and token-level (specific words). Our findings reveal distinct behavioral effects as a function of uncertainty granularity. Token-level uncertainty increased users' agreement with the AI, whereas output- and relation-level uncertainty did not increase agreement but instead reduced users' confidence in their own answers. Notably, relation-level uncertainty also reduced external verification (i.e., internet searches, checking provided URLs), steering users away from independent fact-checking and toward reliance on the LLM and its accompanying uncertainty cues. Our findings demonstrate that uncertainty granularity significantly shapes how users interact with and verify LLM outputs, providing concrete design guidance for building responsible LLM applications that encourage appropriate skepticism and verification behaviors.

Jong Inn Park, Maanas Taneja, Qianwen Wang et al.

Generating engaging, accurate short-form videos from scientific papers is challenging due to content complexity and the gap between expert authors and readers. Existing end-to-end methods often suffer from factual inaccuracies and visual artifacts, limiting their utility for scientific dissemination. To address these issues, we propose SciTalk, a novel multi-LLM agentic framework, grounding videos in various sources, such as text, figures, visual styles, and avatars. Inspired by content creators' workflows, SciTalk uses specialized agents for content summarization, visual scene planning, and text and layout editing, and incorporates an iterative feedback mechanism where video agents simulate user roles to give feedback on generated videos from previous iterations and refine generation prompts. Experimental evaluations show that SciTalk outperforms simple prompting methods in generating scientifically accurate and engaging content over the refined loop of video generation. Although preliminary results are still not yet matching human creators' quality, our framework provides valuable insights into the challenges and benefits of feedback-driven video generation. Our code, data, and generated videos will be publicly available.

Pan Hao, Rishi Selvakumaran, Jacob Sun et al.

Complex visual interfaces are powerful yet have a steep learning curve, as users must navigate feature-rich visual interfaces while reasoning about domain-specific operations. Existing approaches either deliver assistance through a separate chat-based interaction, or require substantial application-specific engineering to build support natively into each interface. To address the gaps, we propose in-situ assistance: a mode of support delivered directly within any live web interface through lightweight, browser-level interventions on the Document Object Model (DOM), without rebuilding the application or modifying its underlying logic. We contribute a design space and a computational pipeline for DOM-mediated in-situ assistance, characterizing how GUI agents can insert, mutate, or recompose web elements to make the interface easier for users to understand, use, and navigate. We instantiate in-situ assistance in DOMSteer, a Chrome extension that interprets a user's help request and live interface context, grounds it to relevant UI elements, and executes reversible DOM manipulations directly on the live page to deliver assistance, including contextual tooltips, control highlighting, layout reorganization. Quantitative evaluations on two complex visual interfaces show that DOMSteer delivers reliable and efficient in-situ assistance. Use cases and a comparative user study with baseline ChatGPTAtlas demonstrate the usability and effectiveness of DOMSteer. Altogether, these findings point to a broader role for GUI agents: not just assisting from the sidelines, but actively reconfiguring live interfaces to support users in the moment.

Shuyu Gan, James Mooney, Pan Hao et al.

Large Language Model (LLM) agents can increasingly automate complex reasoning through Test-Time Scaling (TTS), iterative refinement guided by reward signals. However, many real-world tasks involve multi-stage pipeline whose final outcomes lack verifiable rewards or sufficient data to train robust reward models, making judge-based refinement prone to accumulate error over stages. We propose Selective TTS, a process-based refinement framework that scales inference across different stages in multi-agent pipeline, instead of repeated refinement over time by prior work. By distributing compute across stages and pruning low-quality branches early using process-specific judges, Selective TTS mitigates the judge drift and stabilizes refinement. Grounded in the data science pipeline, we build an end-to-end multi-agent pipeline for generating visually insightful charts and report of given dataset, and design a reliable LLM-based judge model, aligned with human experts (Kendall's τ=0.55). Our proposed selective TTS then improves insight quality under a fixed compute budget, increasing mean scores from 61.64 to 65.86 while reducing variance. We hope our findings serve as the first step toward to scaling complex, open-ended tasks with unverifiable rewards, such as scientific discovery and story generation.

Qianwen Wang, Zhutian Chen, Yong Wang et al.

Inspired by the great success of machine learning (ML), researchers have applied ML techniques to visualizations to achieve a better design, development, and evaluation of visualizations. This branch of studies, known as ML4VIS, is gaining increasing research attention in recent years. To successfully adapt ML techniques for visualizations, a structured understanding of the integration of ML4VISis needed. In this paper, we systematically survey 88 ML4VIS studies, aiming to answer two motivating questions: "what visualization processes can be assisted by ML?" and "how ML techniques can be used to solve visualization problems?" This survey reveals seven main processes where the employment of ML techniques can benefit visualizations:Data Processing4VIS, Data-VIS Mapping, InsightCommunication, Style Imitation, VIS Interaction, VIS Reading, and User Profiling. The seven processes are related to existing visualization theoretical models in an ML4VIS pipeline, aiming to illuminate the role of ML-assisted visualization in general visualizations.Meanwhile, the seven processes are mapped into main learning tasks in ML to align the capabilities of ML with the needs in visualization. Current practices and future opportunities of ML4VIS are discussed in the context of the ML4VIS pipeline and the ML-VIS mapping. While more studies are still needed in the area of ML4VIS, we hope this paper can provide a stepping-stone for future exploration. A web-based interactive browser of this survey is available at https://ml4vis.github.io

Zhihua Jin, Yong Wang, Qianwen Wang et al.

Graph Neural Networks (GNNs) aim to extend deep learning techniques to graph data and have achieved significant progress in graph analysis tasks (e.g., node classification) in recent years. However, similar to other deep neural networks like Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs), GNNs behave like a black box with their details hidden from model developers and users. It is therefore difficult to diagnose possible errors of GNNs. Despite many visual analytics studies being done on CNNs and RNNs, little research has addressed the challenges for GNNs. This paper fills the research gap with an interactive visual analysis tool, GNNLens, to assist model developers and users in understanding and analyzing GNNs. Specifically, Parallel Sets View and Projection View enable users to quickly identify and validate error patterns in the set of wrong predictions; Graph View and Feature Matrix View offer a detailed analysis of individual nodes to assist users in forming hypotheses about the error patterns. Since GNNs jointly model the graph structure and the node features, we reveal the relative influences of the two types of information by comparing the predictions of three models: GNN, Multi-Layer Perceptron (MLP), and GNN Without Using Features (GNNWUF). Two case studies and interviews with domain experts demonstrate the effectiveness of GNNLens in facilitating the understanding of GNN models and their errors.

Qianwen Wang, Zhenhua Xu, Zhutian Chen et al.

The growing use of automated decision-making in critical applications, such as crime prediction and college admission, has raised questions about fairness in machine learning. How can we decide whether different treatments are reasonable or discriminatory? In this paper, we investigate discrimination in machine learning from a visual analytics perspective and propose an interactive visualization tool, DiscriLens, to support a more comprehensive analysis. To reveal detailed information on algorithmic discrimination, DiscriLens identifies a collection of potentially discriminatory itemsets based on causal modeling and classification rules mining. By combining an extended Euler diagram with a matrix-based visualization, we develop a novel set visualization to facilitate the exploration and interpretation of discriminatory itemsets. A user study shows that users can interpret the visually encoded information in DiscriLens quickly and accurately. Use cases demonstrate that DiscriLens provides informative guidance in understanding and reducing algorithmic discrimination.

Qianwen Wang, William Alexander, Jack Pegg et al.

In this paper, we present a visual analytics tool for enabling hypothesis-based evaluation of machine learning (ML) models. We describe a novel ML-testing framework that combines the traditional statistical hypothesis testing (commonly used in empirical research) with logical reasoning about the conclusions of multiple hypotheses. The framework defines a controlled configuration for testing a number of hypotheses as to whether and how some extra information about a "concept" or "feature" may benefit or hinder a ML model. Because reasoning multiple hypotheses is not always straightforward, we provide HypoML as a visual analysis tool, with which, the multi-thread testing data is transformed to a visual representation for rapid observation of the conclusions and the logical flow between the testing data and hypotheses.We have applied HypoML to a number of hypothesized concepts, demonstrating the intuitive and explainable nature of the visual analysis.

Chen Zhu-Tian, Yun Wang, Qianwen Wang et al.

Designers need to consider not only perceptual effectiveness but also visual styles when creating an infographic. This process can be difficult and time consuming for professional designers, not to mention non-expert users, leading to the demand for automated infographics design. As a first step, we focus on timeline infographics, which have been widely used for centuries. We contribute an end-to-end approach that automatically extracts an extensible timeline template from a bitmap image. Our approach adopts a deconstruction and reconstruction paradigm. At the deconstruction stage, we propose a multi-task deep neural network that simultaneously parses two kinds of information from a bitmap timeline: 1) the global information, i.e., the representation, scale, layout, and orientation of the timeline, and 2) the local information, i.e., the location, category, and pixels of each visual element on the timeline. At the reconstruction stage, we propose a pipeline with three techniques, i.e., Non-Maximum Merging, Redundancy Recover, and DL GrabCut, to extract an extensible template from the infographic, by utilizing the deconstruction results. To evaluate the effectiveness of our approach, we synthesize a timeline dataset (4296 images) and collect a real-world timeline dataset (393 images) from the Internet. We first report quantitative evaluation results of our approach over the two datasets. Then, we present examples of automatically extracted templates and timelines automatically generated based on these templates to qualitatively demonstrate the performance. The results confirm that our approach can effectively extract extensible templates from real-world timeline infographics.

Yong Wang, Zhihua Jin, Qianwen Wang et al.

Node-link diagrams are widely used to facilitate network explorations. However, when using a graph drawing technique to visualize networks, users often need to tune different algorithm-specific parameters iteratively by comparing the corresponding drawing results in order to achieve a desired visual effect. This trial and error process is often tedious and time-consuming, especially for non-expert users. Inspired by the powerful data modelling and prediction capabilities of deep learning techniques, we explore the possibility of applying deep learning techniques to graph drawing. Specifically, we propose using a graph-LSTM-based approach to directly map network structures to graph drawings. Given a set of layout examples as the training dataset, we train the proposed graph-LSTM-based model to capture their layout characteristics. Then, the trained model is used to generate graph drawings in a similar style for new networks. We evaluated the proposed approach on two special types of layouts (i.e., grid layouts and star layouts) and two general types of layouts (i.e., ForceAtlas2 and PivotMDS) in both qualitative and quantitative ways. The results provide support for the effectiveness of our approach. We also conducted a time cost assessment on the drawings of small graphs with 20 to 50 nodes. We further report the lessons we learned and discuss the limitations and future work.

Qianwen Wang, Zhen Li, Siwei Fu et al.

Visual designs can be complex in modern data visualization systems, which poses special challenges for explaining them to the non-experts. However, few if any presentation tools are tailored for this purpose. In this study, we present Narvis, a slideshow authoring tool designed for introducing data visualizations to non-experts. Narvis targets two types of end-users: teachers, experts in data visualization who produce tutorials for explaining a data visualization, and students, non-experts who try to understand visualization designs through tutorials. We present an analysis of requirements through close discussions with the two types of end-users. The resulting considerations guide the design and implementation of Narvis. Additionally, to help teachers better organize their introduction slideshows, we specify a data visualization as a hierarchical combination of components, which are automatically detected and extracted by Narvis. The teachers craft an introduction slideshow through first organizing these components, and then explaining them sequentially. A series of templates are provided for adding annotations and animations to improve efficiency during the authoring process. We evaluate Narvis through a qualitative analysis of the authoring experience, and a preliminary evaluation of the generated slideshows.

Qianwen Wang, Yao Ming, Zhihua Jin et al.

To relieve the pain of manually selecting machine learning algorithms and tuning hyperparameters, automated machine learning (AutoML) methods have been developed to automatically search for good models. Due to the huge model search space, it is impossible to try all models. Users tend to distrust automatic results and increase the search budget as much as they can, thereby undermining the efficiency of AutoML. To address these issues, we design and implement ATMSeer, an interactive visualization tool that supports users in refining the search space of AutoML and analyzing the results. To guide the design of ATMSeer, we derive a workflow of using AutoML based on interviews with machine learning experts. A multi-granularity visualization is proposed to enable users to monitor the AutoML process, analyze the searched models, and refine the search space in real time. We demonstrate the utility and usability of ATMSeer through two case studies, expert interviews, and a user study with 13 end users.