April Yi Wang

Chengbo Zheng, Dakuo Wang, April Yi Wang et al.

Creating presentation slides is a critical but time-consuming task for data scientists. While researchers have proposed many AI techniques to lift data scientists' burden on data preparation and model selection, few have targeted the presentation creation task. Based on the needs identified from a formative study, this paper presents NB2Slides, an AI system that facilitates users to compose presentations of their data science work. NB2Slides uses deep learning methods as well as example-based prompts to generate slides from computational notebooks, and take users' input (e.g., audience background) to structure the slides. NB2Slides also provides an interactive visualization that links the slides with the notebook to help users further edit the slides. A follow-up user evaluation with 12 data scientists shows that participants believed NB2Slides can improve efficiency and reduces the complexity of creating slides. Yet, participants questioned the future of full automation and suggested a human-AI collaboration paradigm.

Junling Wang, Boqi Chen, Heejin Do et al.

AI systems are increasingly used to support educational content creation, yet it remains unclear whether they can generate outputs that faithfully represent the pedagogical concepts they are intended to teach. Thus, we introduce equation-to-visual generation, a task that, in contrast to conventional image generation, requires producing pedagogically meaningful visuals from arithmetic equations while precisely preserving their numerical and relational structure. Informed by interviews with teachers and an analysis of educational materials, we construct E2V-Bench, a benchmark spanning four pedagogically grounded visual types, along with automatic metrics for evaluating visual correctness. Our evaluation reveals that recent text-to-image (T2I) models frequently fail on this task, with errors dominated by incorrect object counts and broken relational structure. Building on this, we explore benchmark-guided enhancement strategies. These strategies improve representative models, while the remaining gap calls for stronger numerical and relational grounding in future T2I models.

Zhengxu Li, Junling Wang, April Yi Wang

Generative AI has the potential to help teachers rapidly create classroom-ready visual materials, particularly in mathematics where diagrams and visual representations must be pedagogically meaningful and instructionally correct. However, current generative tools primarily support prompting and post-hoc editing, leaving open a key question for correctness-sensitive educational authoring: when in the generation pipeline should teachers exert control? In this paper, we investigate how the timing of human control in AI-assisted generation shapes teachers' visual authoring practices in correctness-sensitive tasks. We introduce a design space of three stages of control: pre-generation control, where users specify intent solely through natural language prompts before generation; mid-generation control, where users inspect and confirm an explicit layout structure before the system completes generation; and post-generation control, where users directly modify AI-generated visuals after generation through object-level edits. In a within-subject, mixed-methods study with 24 primary mathematics teachers, post-generation control received higher ratings on predictability and correctness, while other subjective measures showed no reliable differences. Qualitative findings explain these differences by revealing workflow trade-offs: highly automated, pre-generation control supports rapid ideation but reduces perceived agency and predictability; mid-generation control improves structural alignment at the cost of additional effort; and post-generation control preserves user agency through low-cost, direct verification and correction. Together, these results suggest that in correctness-sensitive educational tasks, effective generative tools should align system behavior with teacher intent and support stage-dependent workflows that combine automation with direct manipulation.

Junling Wang, Anna Rutkiewicz, April Yi Wang et al.

Visuals are valuable tools for teaching math word problems (MWPs), helping young learners interpret textual descriptions into mathematical expressions before solving them. However, creating such visuals is labor-intensive and there is a lack of automated methods to support this process. In this paper, we present Math2Visual, an automatic framework for generating pedagogically meaningful visuals from MWP text descriptions. Math2Visual leverages a pre-defined visual language and a design space grounded in interviews with math teachers, to illustrate the core mathematical relationships in MWPs. Using Math2Visual, we construct an annotated dataset of 1,903 visuals and evaluate Text-to-Image (TTI) models for their ability to generate visuals that align with our design. We further fine-tune several TTI models with our dataset, demonstrating improvements in educational visual generation. Our work establishes a new benchmark for automated generation of pedagogically meaningful visuals and offers insights into key challenges in producing multimodal educational content, such as the misrepresentation of mathematical relationships and the omission of essential visual elements.

Anjali Khurana, Xiaotian Su, April Yi Wang et al.

Large Language Model (LLM)-based in-application assistants, or copilots, can automate software tasks, but users often prefer learning by doing, raising questions about the optimal level of automation for an effective user experience. We investigated two automation paradigms by designing and implementing a fully automated copilot (AutoCopilot) and a semi-automated copilot (GuidedCopilot) that automates trivial steps while offering step-by-step visual guidance. In a user study (N=20) across data analysis and visual design tasks, GuidedCopilot outperformed AutoCopilot in user control, software utility, and learnability, especially for exploratory and creative tasks, while AutoCopilot saved time for simpler visual tasks. A follow-up design exploration (N=10) enhanced GuidedCopilot with task-and state-aware features, including in-context preview clips and adaptive instructions. Our findings highlight the critical role of user control and tailored guidance in designing the next generation of copilots that enhance productivity, support diverse skill levels, and foster deeper software engagement.

Elizaveta Artser, Daniil Karol, Anna Potriasaeva et al.

Debugging is a crucial skill in programming education and software development, yet it is often overlooked in CS curricula. To address this, we introduce an AI-powered debugging assistant integrated into an IDE. It offers real-time support by analyzing code, suggesting breakpoints, and providing contextual hints. Using RAG with LLMs, program slicing, and custom heuristics, it enhances efficiency by minimizing LLM calls and improving accuracy. A three-level evaluation - technical analysis, UX study, and classroom tests - highlights its potential for teaching debugging.

Bingsheng Yao, Jiaju Chen, Chaoran Chen et al.

Intelligent systems have traditionally been designed as tools rather than collaborators, often lacking critical characteristics that collaboration partnerships require. Recent advances in large language model (LLM) agents open new opportunities for human-LLM-agent collaboration by enabling natural communication and various social and cognitive behaviors. Yet it remains unclear whether principles of computer-mediated collaboration established in HCI and CSCW persist, change, or fail when humans collaborate with LLM agents. To support systematic investigations of these questions, we introduce an open and configurable research platform for HCI researchers. The platform's modular design allows seamless adaptation of classic CSCW experiments and manipulation of theory-grounded interaction controls. We demonstrate the platform's effectiveness and usability through two case studies: (1) re-implementing the classic human-human-collaboration task Shape Factory as a between-subject human-agent-collaboration experiment with 16 participants, and (2) a participatory cognitive walkthrough with five HCI researchers to refine workflows and interfaces for experiment setup and analysis.

Dakuo Wang, Xiaojuan Ma, April Yi Wang

Human-Centered AI (HCAI) refers to the research effort that aims to design and implement AI techniques to support various human tasks, while taking human needs into consideration and preserving human control. In this short position paper, we illustrate how we approach HCAI using a series of research projects around Data Science (DS) works as a case study. The AI techniques built for supporting DS works are collectively referred to as AutoML systems, and their goals are to automate some parts of the DS workflow. We illustrate a three-step systematical research approach(i.e., explore, build, and integrate) and four practical ways of implementation for HCAI systems. We argue that our work is a cornerstone towards the ultimate future of Human-AI Collaboration for DS and beyond, where AI and humans can take complementary and indispensable roles to achieve a better outcome and experience.

Xuye Liu, Dakuo Wang, April Wang et al.

Jupyter notebook allows data scientists to write machine learning code together with its documentation in cells. In this paper, we propose a new task of code documentation generation (CDG) for computational notebooks. In contrast to the previous CDG tasks which focus on generating documentation for single code snippets, in a computational notebook, one documentation in a markdown cell often corresponds to multiple code cells, and these code cells have an inherent structure. We proposed a new model (HAConvGNN) that uses a hierarchical attention mechanism to consider the relevant code cells and the relevant code tokens information when generating the documentation. Tested on a new corpus constructed from well-documented Kaggle notebooks, we show that our model outperforms other baseline models.

April Yi Wang, Dakuo Wang, Jaimie Drozdal et al.

Computational notebooks allow data scientists to express their ideas through a combination of code and documentation. However, data scientists often pay attention only to the code, and neglect creating or updating their documentation during quick iterations. Inspired by human documentation practices learned from 80 highly-voted Kaggle notebooks, we design and implement Themisto, an automated documentation generation system to explore how human-centered AI systems can support human data scientists in the machine learning code documentation scenario. Themisto facilitates the creation of documentation via three approaches: a deep-learning-based approach to generate documentation for source code, a query-based approach to retrieve online API documentation for source code, and a user prompt approach to nudge users to write documentation. We evaluated Themisto in a within-subjects experiment with 24 data science practitioners, and found that automated documentation generation techniques reduced the time for writing documentation, reminded participants to document code they would have ignored, and improved participants' satisfaction with their computational notebook.

Soya Park, April Wang, Ban Kawas et al.

Data scientists face a steep learning curve in understanding a new domain for which they want to build machine learning (ML) models. While input from domain experts could offer valuable help, such input is often limited, expensive, and generally not in a form readily consumable by a model development pipeline. In this paper, we propose Ziva, a framework to guide domain experts in sharing essential domain knowledge to data scientists for building NLP models. With Ziva, experts are able to distill and share their domain knowledge using domain concept extractors and five types of label justification over a representative data sample. The design of Ziva is informed by preliminary interviews with data scientists, in order to understand current practices of domain knowledge acquisition process for ML development projects. To assess our design, we run a mix-method case-study to evaluate how Ziva can facilitate interaction of domain experts and data scientists. Our results highlight that (1) domain experts are able to use Ziva to provide rich domain knowledge, while maintaining low mental load and stress levels; and (2) data scientists find Ziva's output helpful for learning essential information about the domain, offering scalability of information, and lowering the burden on domain experts to share knowledge. We conclude this work by experimenting with building NLP models using the Ziva output by our case study.