Search

Novice programmers are increasingly relying on Large Language Models (LLMs) to generate code for learning programming concepts. However, this interaction can lead to superficial engagement, giving learners an illusion of learning and hindering skill development. To address this issue, we conducted a systematic design exploration to develop seven cognitive engagement techniques aimed at promoting deeper engagement with AI-generated code. In this paper, we describe our design process, the initial seven techniques and results from a between-subjects study (N=82). We then iteratively refined the top techniques and further evaluated them through a within-subjects study (N=42). We evaluate the friction each technique introduces, their effectiveness in helping learners apply concepts to isomorphic tasks without AI assistance, and their success in aligning learners' perceived and actual coding abilities. Ultimately, our results highlight the most effective technique: guiding learners through the step-by-step problem-solving process, where they engage in an interactive dialog with the AI, prompting what needs to be done at each stage before the corresponding code is revealed., Comment: 19 pages, 6 figures

Research ideation involves broad exploring and deep refining ideas. Both require deep engagement with literature. Existing tools focus primarily on idea broad generation, yet offer little support for iterative specification, refinement, and evaluation needed to further develop initial ideas. To bridge this gap, we introduce IdeaSynth, a research idea development system that uses LLMs to provide literature-grounded feedback for articulating research problems, solutions, evaluations, and contributions. IdeaSynth represents these idea facets as nodes on a canvas, and allow researchers to iteratively refine them by creating and exploring variations and composing them. Our lab study (N=20) showed that participants, while using IdeaSynth, explored more alternative ideas and expanded initial ideas with more details compared to a strong LLM-based baseline. Our deployment study (N=7) demonstrated that participants effectively used IdeaSynth for real-world research projects at various ideation stages from developing initial ideas to revising framings of mature manuscripts, highlighting the possibilities to adopt IdeaSynth in researcher's workflows.

Mixed Reality enables hybrid workspaces where physical and virtual monitors are adaptively created and moved to suit the current environment and needs. However, in shared settings, individual users' workspaces are rarely aligned and can vary significantly in the number of monitors, available physical space, and workspace layout, creating inconsistencies between workspaces which may cause confusion and reduce collaboration. We present Desk2Desk, an optimization-based approach for remote collaboration in which the hybrid workspaces of two collaborators are fully integrated to enable immersive side-by-side collaboration. The optimization adjusts each user's workspace in layout and number of shared monitors and creates a mapping between workspaces to handle inconsistencies between workspaces due to physical constraints (e.g. physical monitors). We show in a user study how our system adaptively merges dissimilar physical workspaces to enable immersive side-by-side collaboration, and demonstrate how an optimization-based approach can effectively address dissimilar physical layouts., Comment: ACM Symposium on User Interface Software and Technology (UIST '24)

LLM-powered tools like ChatGPT Data Analysis, have the potential to help users tackle the challenging task of data analysis programming, which requires expertise in data processing, programming, and statistics. However, our formative study (n=15) uncovered serious challenges in verifying AI-generated results and steering the AI (i.e., guiding the AI system to produce the desired output). We developed two contrasting approaches to address these challenges. The first (Stepwise) decomposes the problem into step-by-step subgoals with pairs of editable assumptions and code until task completion, while the second (Phasewise) decomposes the entire problem into three editable, logical phases: structured input/output assumptions, execution plan, and code. A controlled, within-subjects experiment (n=18) compared these systems against a conversational baseline. Users reported significantly greater control with the Stepwise and Phasewise systems, and found intervention, correction, and verification easier, compared to the baseline. The results suggest design guidelines and trade-offs for AI-assisted data analysis tools., Comment: Published at UIST 2024; 19 pages, 9 figures, and 2 tables

The progression to "Pervasive Augmented Reality" envisions easy access to multimodal information continuously. However, in many everyday scenarios, users are occupied physically, cognitively or socially. This may increase the friction to act upon the multimodal information that users encounter in the world. To reduce such friction, future interactive interfaces should intelligently provide quick access to digital actions based on users' context. To explore the range of possible digital actions, we conducted a diary study that required participants to capture and share the media that they intended to perform actions on (e.g., images or audio), along with their desired actions and other contextual information. Using this data, we generated a holistic design space of digital follow-up actions that could be performed in response to different types of multimodal sensory inputs. We then designed OmniActions, a pipeline powered by large language models (LLMs) that processes multimodal sensory inputs and predicts follow-up actions on the target information grounded in the derived design space. Using the empirical data collected in the diary study, we performed quantitative evaluations on three variations of LLM techniques (intent classification, in-context learning and finetuning) and identified the most effective technique for our task. Additionally, as an instantiation of the pipeline, we developed an interactive prototype and reported preliminary user feedback about how people perceive and react to the action predictions and its errors., Comment: Paper accepted to the 2024 CHI Conference on Human Factors in Computing Systems (CHI 2024)

Timely, personalized feedback is essential for students learning programming. LLM-powered tools like ChatGPT offer instant support, but reveal direct answers with code, which may hinder deep conceptual engagement. We developed CodeAid, an LLM-powered programming assistant delivering helpful, technically correct responses, without revealing code solutions. CodeAid answers conceptual questions, generates pseudo-code with line-by-line explanations, and annotates student's incorrect code with fix suggestions. We deployed CodeAid in a programming class of 700 students for a 12-week semester. A thematic analysis of 8,000 usages of CodeAid was performed, further enriched by weekly surveys, and 22 student interviews. We then interviewed eight programming educators to gain further insights. Our findings reveal four design considerations for future educational AI assistants: D1) exploiting AI's unique benefits; D2) simplifying query formulation while promoting cognitive engagement; D3) avoiding direct responses while encouraging motivated learning; and D4) maintaining transparency and control for students to asses and steer AI responses., Comment: CHI 2024 Paper - The paper includes 17 pages, 8 figures, 2 tables, along with a 2-page appendix

Synthesizers are powerful tools that allow musicians to create dynamic and original sounds. Existing commercial interfaces for synthesizers typically require musicians to interact with complex low-level parameters or to manage large libraries of premade sounds. To address these challenges, we implement SynthScribe -- a fullstack system that uses multimodal deep learning to let users express their intentions at a much higher level. We implement features which address a number of difficulties, namely 1) searching through existing sounds, 2) creating completely new sounds, 3) making meaningful modifications to a given sound. This is achieved with three main features: a multimodal search engine for a large library of synthesizer sounds; a user centered genetic algorithm by which completely new sounds can be created and selected given the users preferences; a sound editing support feature which highlights and gives examples for key control parameters with respect to a text or audio based query. The results of our user studies show SynthScribe is capable of reliably retrieving and modifying sounds while also affording the ability to create completely new sounds that expand a musicians creative horizon.

Exploring alternative ideas by rewriting text is integral to the writing process. State-of-the-art Large Language Models (LLMs) can simplify writing variation generation. However, current interfaces pose challenges for simultaneous consideration of multiple variations: creating new variations without overwriting text can be difficult, and pasting them sequentially can clutter documents, increasing workload and disrupting writers' flow. To tackle this, we present ABScribe, an interface that supports rapid, yet visually structured, exploration and organization of writing variations in human-AI co-writing tasks. With ABScribe, users can swiftly modify variations using LLM prompts, which are auto-converted into reusable buttons. Variations are stored adjacently within text fields for rapid in-place comparisons using mouse-over interactions on a popup toolbar. Our user study with 12 writers shows that ABScribe significantly reduces task workload (d = 1.20, p < 0.001), enhances user perceptions of the revision process (d = 2.41, p < 0.001) compared to a popular baseline workflow, and provides insights into how writers explore variations using LLMs., Comment: CHI 2024

As Large Language Models (LLMs) gain in popularity, it is important to understand how novice programmers use them. We present a thematic analysis of 33 learners, aged 10-17, independently learning Python through 45 code-authoring tasks using Codex, an LLM-based code generator. We explore several questions related to how learners used these code generators and provide an analysis of the properties of the written prompts and the generated code. Specifically, we explore (A) the context in which learners use Codex, (B) what learners are asking from Codex, (C) properties of their prompts in terms of relation to task description, language, and clarity, and prompt crafting patterns, (D) the correctness, complexity, and accuracy of the AI-generated code, and (E) how learners utilize AI-generated code in terms of placement, verification, and manual modifications. Furthermore, our analysis reveals four distinct coding approaches when writing code with an AI code generator: AI Single Prompt, where learners prompted Codex once to generate the entire solution to a task; AI Step-by-Step, where learners divided the problem into parts and used Codex to generate each part; Hybrid, where learners wrote some of the code themselves and used Codex to generate others; and Manual coding, where learners wrote the code themselves. The AI Single Prompt approach resulted in the highest correctness scores on code-authoring tasks, but the lowest correctness scores on subsequent code-modification tasks during training. Our results provide initial insight into how novice learners use AI code generators and the challenges and opportunities associated with integrating them into self-paced learning environments. We conclude with various signs of over-reliance and self-regulation, as well as opportunities for curriculum and tool development., Comment: 12 pages, Peer-Reviewed, Accepted for publication in the proceedings of the 2023 ACM Koli Calling International Conference on Computing Education Research

Many XR devices use bare-hand gestures to reduce the need for handheld controllers. Such gestures, however, lead to false positive and false negative recognition errors, which detract from the user experience. While mediation techniques enable users to overcome recognition errors by clarifying their intentions via UI elements, little research has explored how mediation techniques should be designed in XR and how a user's task and context may impact their design preferences. This research presents empirical studies about the impact of user perceived error costs on users' preferences for three mediation technique designs, under different simulated scenarios that were inspired by real-life tasks. Based on a large-scale crowd-sourced survey and an immersive VR-based user study, our results suggest that the varying contexts within each task type can impact users' perceived error costs, leading to different preferred mediation techniques. We further discuss the study implications of these results on future XR interaction design., Comment: IEEE International Symposium on Mixed and Augmented Reality (ISMAR), 2023

Knowledge workers frequently encounter repetitive web data entry tasks, like updating records or placing orders. Web automation increases productivity, but translating tasks to web actions accurately and extending to new specifications is challenging. Existing tools can automate tasks that perform the same logical trace of UI actions (e.g., input text in each field in order), but do not support tasks requiring different executions based on varied input conditions. We present DiLogics, a programming-by-demonstration system that utilizes NLP to assist users in creating web automation programs that handle diverse specifications. DiLogics first semantically segments input data to structured task steps. By recording user demonstrations for each step, DiLogics generalizes the web macros to novel but semantically similar task requirements. Our evaluation showed that non-experts can effectively use DiLogics to create automation programs that fulfill diverse input instructions. DiLogics provides an efficient, intuitive, and expressive method for developing web automation programs satisfying diverse specifications.

Text-to-image generative models have demonstrated remarkable capabilities in generating high-quality images based on textual prompts. However, crafting prompts that accurately capture the user's creative intent remains challenging. It often involves laborious trial-and-error procedures to ensure that the model interprets the prompts in alignment with the user's intention. To address the challenges, we present Promptify, an interactive system that supports prompt exploration and refinement for text-to-image generative models. Promptify utilizes a suggestion engine powered by large language models to help users quickly explore and craft diverse prompts. Our interface allows users to organize the generated images flexibly, and based on their preferences, Promptify suggests potential changes to the original prompt. This feedback loop enables users to iteratively refine their prompts and enhance desired features while avoiding unwanted ones. Our user study shows that Promptify effectively facilitates the text-to-image workflow and outperforms an existing baseline tool widely used for text-to-image generation.

Live and pre-recorded video tutorials are an effective means for teaching physical skills such as cooking or prototyping electronics. A dedicated cameraperson following an instructor's activities can improve production quality. However, instructors who do not have access to a cameraperson's help often have to work within the constraints of static cameras. We present Stargazer, a novel approach for assisting with tutorial content creation with a camera robot that autonomously tracks regions of interest based on instructor actions to capture dynamic shots. Instructors can adjust the camera behaviors of Stargazer with subtle cues, including gestures and speech, allowing them to fluidly integrate camera control commands into instructional activities. Our user study with six instructors, each teaching a distinct skill, showed that participants could create dynamic tutorial videos with a diverse range of subjects, camera framing, and camera angle combinations using Stargazer., Comment: To appear in Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems (CHI '23), April 23--28, 2023, Hamburg, Germany

AI code generators like OpenAI Codex have the potential to assist novice programmers by generating code from natural language descriptions, however, over-reliance might negatively impact learning and retention. To explore the implications that AI code generators have on introductory programming, we conducted a controlled experiment with 69 novices (ages 10-17). Learners worked on 45 Python code-authoring tasks, for which half of the learners had access to Codex, each followed by a code-modification task. Our results show that using Codex significantly increased code-authoring performance (1.15x increased completion rate and 1.8x higher scores) while not decreasing performance on manual code-modification tasks. Additionally, learners with access to Codex during the training phase performed slightly better on the evaluation post-tests conducted one week later, although this difference did not reach statistical significance. Of interest, learners with higher Scratch pre-test scores performed significantly better on retention post-tests, if they had prior access to Codex., Comment: To be published in Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems (CHI '23), April 23--28, 2023, Hamburg, Germany 17 pages with 11 Figures, 2 Tables, 6 Page Appendix

Transitioning from block-based programming to text-based programming environments can be challenging as it requires students to learn new programming language concepts. In this paper, we identify and classify the issues encountered when transitioning from block-based to text-based programming. In particular, we investigate differences that emerge in learners when using a structured editor compared to an unstructured editor. We followed 26 high school students (ages 12-16; M=14 years) as they transitioned from Scratch to Python in three phases: (i) learning Scratch, (ii) transitioning from Scratch to Python using either a structured or unstructured editor, and (iii) evaluating Python coding skills using an unstructured editor. We identify 27 distinct types of issues and show that learners who used a structured editor during the transition phase had 4.6x less syntax issues and 1.9x less data-type issues compared to those who did not. When these learners switched to an unstructured editor for evaluation, they kept a lower rate on data-type issues but faced 4x more syntax errors., Comment: To be published in Proceedings of the 2023 SIGCSE technical symposium on computer science education, 7 pages, 3 figures

Mobile User Interface Summarization generates succinct language descriptions of mobile screens for conveying important contents and functionalities of the screen, which can be useful for many language-based application scenarios. We present Screen2Words, a novel screen summarization approach that automatically encapsulates essential information of a UI screen into a coherent language phrase. Summarizing mobile screens requires a holistic understanding of the multi-modal data of mobile UIs, including text, image, structures as well as UI semantics, motivating our multi-modal learning approach. We collected and analyzed a large-scale screen summarization dataset annotated by human workers. Our dataset contains more than 112k language summarization across $\sim$22k unique UI screens. We then experimented with a set of deep models with different configurations. Our evaluation of these models with both automatic accuracy metrics and human rating shows that our approach can generate high-quality summaries for mobile screens. We demonstrate potential use cases of Screen2Words and open-source our dataset and model to lay the foundations for further bridging language and user interfaces., Comment: UIST'21

In ad-hoc human-robot collaboration (HRC), humans and robots work on a task without pre-planning the robot's actions prior to execution; instead, task allocation occurs in real-time. However, prior research has largely focused on task allocations that are pre-planned - there has not been a comprehensive exploration or evaluation of techniques where task allocation is adjusted in real-time. Inspired by HCI research on territoriality and proxemics, we propose a design space of novel task allocation techniques including both explicit techniques, where the user maintains agency, and implicit techniques, where the efficiency of automation can be leveraged. The techniques were implemented and evaluated using a tabletop HRC simulation in VR. A 16-participant study, which presented variations of a collaborative block stacking task, showed that implicit techniques enable efficient task completion and task parallelization, and should be augmented with explicit mechanisms to provide users with fine-grained control., Comment: To be published in Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems

Learning musical instruments using online instructional videos has become increasingly prevalent. However, pre-recorded videos lack the instantaneous feedback and personal tailoring that human tutors provide. In addition, existing video navigations are not optimized for instrument learning, making the learning experience encumbered. Guided by our formative interviews with guitar players and prior literature, we designed Soloist, a mixed-initiative learning framework that automatically generates customizable curriculums from off-the-shelf guitar video lessons. Soloist takes raw videos as input and leverages deep-learning based audio processing to extract musical information. This back-end processing is used to provide an interactive visualization to support effective video navigation and real-time feedback on the user's performance, creating a guided learning experience. We demonstrate the capabilities and specific use-cases of Soloist within the domain of learning electric guitar solos using instructional YouTube videos. A remote user study, conducted to gather feedback from guitar players, shows encouraging results as the users unanimously preferred learning with Soloist over unconverted instructional videos., Comment: ACM CHI 2021 Camera-Ready, Single Column