HEPHA: A Mixed-Initiative Image Labeling Tool for Specialized DomainsImage labeling is an important task for training computer vision models. In specialized domains, such as healthcare, it is expensive and challenging to recruit specialists for image labeling. We propose HEPHA, a mixed-initiative image labeling tool that elicits human expertise via inductive logic learning to infer and…2025SZShiyuan Zhou et al.Computer ScienceExplainable AI (XAI)Interactive Data VisualizationMedical & Scientific Data VisualizationIUI
Text-to-SQL Domain Adaptation via Human-LLM Collaborative Data AnnotationText-to-SQL models, which parse natural language (NL) questions to executable SQL queries, are increasingly adopted in real-world applications. However, deploying such models in the real world often requires adapting them to the highly specialized database schemas used in specific applications. We observe that the per…2025YTYuan Tian et al.Purdue UniversityHuman-LLM CollaborationAutoML InterfacesIUI
Dango: A Mixed-Initiative Data Wrangling System using Large Language ModelData wrangling is a time-consuming and challenging task in the early stages of a data science pipeline. However, existing tools often fail to effectively interpret user intent. We propose Dango, a mixed-initiative multi-agent system that helps users generate data wrangling scripts. Compared to existing tools, Dango en…2025WCWei-Hao Chen et al.Purdue UniversityHuman-LLM CollaborationAI-Assisted Decision-Making & AutomationInteractive Data VisualizationCHI
SQLucid: Grounding Natural Language Database Queries with Interactive ExplanationsThough recent advances in machine learning have led to significant improvements in natural language interfaces for databases, the accuracy and reliability of these systems remain limited, especially in high-stakes domains. This paper introduces SQLucid, a novel user interface that bridges the gap between non-expert us…2024YTYuan Tian et al.Purdue UniversityExplainable AI (XAI)AI-Assisted Decision-Making & AutomationUIST
PromptCharm: Text-to-Image Generation through Multi-modal Prompting and RefinementThe recent advancements in Generative AI have significantly advanced the field of text-to-image generation. The state-of-the-art text-to-image model, Stable Diffusion, is now capable of synthesizing high-quality images with a strong sense of aesthetics. Crafting text prompts that align with the model's interpretation…2024ZWZhijie Wang et al.University of AlbertaGenerative AI (Text, Image, Music, Video)Explainable AI (XAI)AI-Assisted Creative WritingCHI
STILE: Exploring and Debugging Social Biases in Pre-trained Text RepresentationsThe recent success of Natural Language Processing (NLP) relies heavily on pre-trained text representations such as word embeddings. However, pre-trained text representations may exhibit social biases and stereotypes, e.g., disproportionately associating gender with occupations. Though prior work presented various bias…2024SKSamia Kabir et al.Purdue UniversityAI Ethics, Fairness & AccountabilityAlgorithmic Fairness & BiasCHI
Is Stack Overflow Obsolete? An Empirical Study of the Characteristics of ChatGPT Answers to Stack Overflow QuestionsQ&A platforms have been crucial for the online help-seeking behavior of programmers. However, the recent popularity of ChatGPT is altering this trend. Despite this popularity, no comprehensive study has been conducted to evaluate the characteristics of ChatGPT’s answers to programming questions. To bridge the gap, we…2024SKSamia Kabir et al.Purdue UniversityHuman-LLM CollaborationAI-Assisted Decision-Making & AutomationAI Ethics, Fairness & AccountabilityCHI
MIWA: Mixed-Initiative Web Automation for Better User Control and ConfidenceIn the era of Big Data, web automation is frequently used by data scientists, domain experts, and programmers to complete time-consuming data collection tasks. However, developing web automation scripts requires familiarity with a programming language and HTML, which remains a key learning barrier for non-expert users…2023WCWeihao Chen et al.Purdue UniversityExplainable AI (XAI)AI-Assisted Decision-Making & AutomationUIST
DeepSeer: Interactive RNN Explanation and Debugging via State AbstractionRecurrent Neural Networks (RNNs) have been widely used in Natural Language Processing (NLP) tasks given its superior performance on processing sequential data. However, it is challenging to interpret and debug RNNs due to the inherent complexity and the lack of transparency of RNNs. While many explainable AI (XAI) tec…2023ZWZhijie Wang et al.University of AlbertaExplainable AI (XAI)Computational Methods in HCICHI
DeepLens: Interactive Out-of-distribution Data Detection in NLP ModelsMachine Learning (ML) has been widely used in Natural Language Processing (NLP) applications. A fundamental assumption in ML is that training data and real-world data should follow a similar distribution. However, a deployed ML model may suffer from out-of-distribution (OOD) issues due to distribution shifts in the re…2023DSDa Song et al.University of AlbertaExplainable AI (XAI)Algorithmic Transparency & AuditabilityComputational Methods in HCICHI
Concept-Labeled Examples for Library ComparisonProgrammers often rely on online resources—such as code examples, documentation, blogs, and Q&A forums—to compare similar libraries and select the one most suitable for their own tasks and contexts. However, this comparison task is often done in an ad-hoc manner, which may result in suboptimal choices. Inspired by Ana…2022LYLitao Yan et al.Harvard UniversityKnowledge Worker Tools & WorkflowsPrototyping & User TestingUIST
INTENT: Interactive Tensor Transformation SynthesisThere is a growing interest in adopting Deep Learning (DL) given its superior performance in many domains. However, modern DL frameworks such as TensorFlow often come with a steep learning curve. In this work, we propose INTENT, an interactive system that infers user intent and generates corresponding TensorFlow code…2022ZZZhanhui Zhou et al.University of MichiganAutoML InterfacesComputational Methods in HCIUIST
Visualizing Examples of Deep Neural Networks at ScaleMany programmers want to use deep learning due to its superior accuracy in many challenging domains. Yet our formative study with ten programmers indicated that, when constructing their own deep neural networks (DNNs), they often had a difficult time choosing appropriate model structures and hyperparameter values. Thi…2021LYLitao Yan et al.Harvard UniversityHuman-LLM CollaborationInteractive Data VisualizationCHI
Interpretable Program SynthesisProgram synthesis, which generates programs based on user-provided specifications, can be obscure and brittle: users have few ways to understand and recover from synthesis failures. We propose interpretable program synthesis, a novel approach that unveils the synthesis process and enables users to monitor and guide th…2021TZTianyi Zhang et al.Purdue UniversityExplainable AI (XAI)Prototyping & User TestingCHI
Interactive Program Synthesis by Augmented ExamplesProgramming-by-example (PBE) has become an increasingly popular component in software development tools, humanrobot interaction, and end-user programming. A long-standing challenge in PBE is the inherent ambiguity in user-provided examples. This paper presents an interaction model to disambiguate user intent and reduc…2020TZTianyi Zhang et al.Purdue UniversityProgramming Education & Computational ThinkingComputational Methods in HCIUIST
Enabling Data-Driven API Design with Community Usage Data: A Need-Finding StudyAPIs are becoming the fundamental building block of modern software and their usability is crucial to programming efficiency and software quality. Yet API designers find it hard to gather and interpret user feedback on their APIs. To close the gap, we interviewed 23 API designers from 6 companies and 11 open-source pr…2020TZTianyi Zhang et al.Purdue UniversityComputational Methods in HCICHI