Conversational AI agents are commonly applied within single-user, turn-taking scenarios. The interaction mechanics of these scenarios are trivial: when the user enters a message, the AI agent produces a response. However, the interaction dynamics are more complex within group settings. How should an agent behave in these settings? We report on two experiments aimed at uncovering users' experiences of an AI agent's participation within a group, in the context of group ideation (brainstorming). In the first study, participants benefited from and preferred having the AI agent in the group, but participants disliked when the agent seemed to dominate the conversation and they desired various controls over its interactive behaviors. In the second study, we created functional controls over the agent's behavior, operable by group members, to validate their utility and probe for additional requirements. Integrating our findings across both studies, we developed a taxonomy of controls for when, what, and where a conversational AI agent in a group should respond, who can control its behavior, and how those controls are specified and implemented. Our taxonomy is intended to aid AI creators to think through important considerations in the design of mixed-initiative conversational agents.

Generative AI applications present unique design challenges. As generative AI technologies are increasingly being incorporated into mainstream applications, there is an urgent need for guidance on how to design user experiences that foster effective and safe use. We present six principles for the design of generative AI applications that address unique characteristics of generative AI UX and offer new interpretations and extensions of known issues in the design of AI applications. Each principle is coupled with a set of design strategies for implementing that principle via UX capabilities or through the design process. The principles and strategies were developed through an iterative process involving literature review, feedback from design practitioners, validation against real-world generative AI applications, and incorporation into the design process of two generative AI applications. We anticipate the principles to usefully inform the design of generative AI applications by driving actionable design recommendations.

Large language models (LLMs) have recently been applied in software engineering to perform tasks such as translating code between programming languages, generating code from natural language, and autocompleting code as it is being written. When used within development tools, these systems typically treat each model invocation independently from all previous invocations, and only a specific limited functionality is exposed within the user interface. This approach to user interaction misses an opportunity for users to more deeply engage with the model by having the context of their previous interactions, as well as the context of their code, inform the model’s responses. We developed a prototype system – the Programmer’s Assistant – in order to explore the utility of conversational interactions grounded in code, as well as software engineers’ receptiveness to the idea of conversing with, rather than invoking, a code-fluent LLM. Through an evaluation with 42 participants with varied levels of programming experience, we found that our system was capable of conducting extended, multi-turn discussions, and that it enabled additional knowledge and capabilities beyond code generation to emerge from the LLM. Despite skeptical initial expectations for conversational programming assistance, participants were impressed by the breadth of the assistant’s capabilities, the quality of its responses, and its potential for improving their productivity. Our work demonstrates the unique potential of conversational interactions with LLMs for co-creative processes like software development.

What does it mean for a generative AI model to be explainable? The emergent discipline of explainable AI (XAI) has made great strides in helping people understand discriminative models. Less attention has been paid to generative models that produce artifacts, rather than decisions, as output. Meanwhile, generative AI (GenAI) technologies are maturing and being applied to application domains such as software engineering. Using scenario-based design and question-driven XAI design approaches, we explore users’ explainability needs for GenAI in three software engineering use cases: natural language to code, code translation, and code auto-completion. We conducted 9 workshops with 43 software engineers in which real examples from state-of-the-art generative AI models were used to elicit users’ explainability needs. Drawing from prior work, we also propose 4 types of XAI features for GenAI for code and gathered additional design ideas from participants. Our work explores explainability needs for GenAI for code and demonstrates how human-centered approaches can drive the technical development of XAI in novel domains.

Generative machine learning models have recently been applied to source code, for use cases including translating code between programming languages, creating documentation from code, and auto-completing methods. Yet, state-of-the-art models often produce code that is erroneous or incomplete. In a controlled study with 32 software engineers, we examined whether such imperfect outputs are helpful in the context of Java-to-Python code translation. When aided by the outputs of a code translation model, participants produced code with fewer errors than when working alone. We also examined how the quality and quantity of AI translations affected the work process and quality of outcomes, and observed that providing multiple translations had a larger impact on the translation process than varying the quality of provided translations. Our results tell a complex, nuanced story about the benefits of generative code models and the challenges software engineers face when working with their outputs. Our work motivates the need for intelligent user interfaces that help software engineers effectively work with generative code models in order to understand and evaluate their outputs and achieve superior outcomes to working alone.

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.

As AI-powered systems increasingly mediate consequential decision-making, their explainability is critical for end-users to take informed and accountable actions. Explanations in human-human interactions are socially-situated. AI systems are often socio-organizationally embedded. However, Explainable AI (XAI) approaches have been predominantly algorithm-centered. We take a developmental step towards socially-situated XAI by introducing and exploring Social Transparency (ST), a sociotechnically informed perspective that incorporates the socio-organizational context into explaining AI-mediated decision-making. To explore ST conceptually, we conducted interviews with 29 AI users and practitioners grounded in a speculative design scenario. We suggested constitutive design elements of ST and developed a conceptual framework to unpack ST’s effect and implications at the technical, decision-making, and organizational level. The framework showcases how ST can potentially calibrate trust in AI, improve decision-making, facilitate organizational collective actions, and cultivate holistic explainability. Our work contributes to the discourse of Human-Centered XAI by expanding the design space of XAI.

Data science (DS) projects often follow a lifecycle that consists of laborious tasks for data scientists and domain experts (e.g., data exploration, model training, etc.). Only till recently, machine learning(ML) researchers have developed promising automation techniques to aid data workers in these tasks. This paper introduces AutoDS, an automated machine learning (AutoML) system that aims to leverage the latest ML automation techniques to support data science projects. Data workers only need to upload their dataset, then the system can automatically suggest ML configurations, preprocess data, select algorithm, and train the model. These suggestions are presented to the user via a web-based graphical user interface and a notebook-based programming user interface. Our goal is to offer a systematic investigation of user interaction and perceptions of using an AutoDS system in solving a data science task. We studied AutoDS with 30 professional data scientists, where one group used AutoDS, and the other did not, to complete a data science project. As expected, AutoDS improves productivity; Yet surprisingly, we find that the models produced by the AutoDS group have higher quality and less errors, but lower human confidence scores. We reflect on the findings by presenting design implications for incorporating automation techniques into human work in the data science lifecycle.

Automated Machine Learning (AutoML) is a rapidly growing set of technologies that automate the model development pipeline by searching model space and generating candidate models. A critical, final step of AutoML is human selection of a final model from dozens of candidates. In current AutoML systems, selection is supported only by performance metrics. Prior work has shown that in practice, people evaluate ML models based on additional criteria, such as the way a model makes predictions. Comparison may happen at multiple levels, from types of errors, to feature importance, to how the model makes predictions of specific instances. We developed Model LineUpper to support interactive model comparison for AutoML by integrating multiple Explainable AI (XAI) and visualization techniques. We conducted a user study in which we both evaluated the system and used it as a technology probe to understand how users perform model comparison in an AutoML system. We discuss design implications for utilizing XAI techniques for model comparison and supporting the unique needs of data scientists in comparing AutoML models.

Generative models have become adept at producing artifacts such as images, videos, and prose at human-like levels of proficiency. New generative techniques, such as unsupervised neural machine translation (NMT), have recently been applied to the task of generating source code, translating it from one programming language to another. The artifacts produced in this way may contain imperfections, such as compilation or logical errors. We examine the extent to which software engineers would tolerate such imperfections and explore ways to aid the detection and correction of those errors. Using a design scenario approach, we interviewed 11 software engineers to understand their reactions to the use of an NMT model in the context of application modernization, focusing on the task of translating source code from one language to another. Our three-stage scenario sparked discussions about the utility and desirability of working with an imperfect AI system, how acceptance of that system’s outputs would be established, and future opportunities for generative AI in application modernization. Our study highlights how UI features such as confidence highlighting and alternate translations help software engineers work with and better understand generative NMT models.

We explore trust in a relatively new area of data science: Automated Machine Learning (AutoML). In AutoML, AI methods are used to generate and optimize machine learning models by automatically engineering features, selecting models, and optimizing hyperparameters. In this paper, we seek to understand what kinds of information influence data scientists' trust in the models produced by AutoML? We operationalize trust as a willingness to deploy a model produced using automated methods. We report results from three studies - qualitative interviews, a controlled experiment, and a card-sorting task - to understand the information needs of data scientists for establishing trust in AutoML systems. We find that including transparency features in an AutoML tool increased user trust and understandability in the tool; and out of all proposed features, model performance metrics and visualizations are the most important information to data scientists when establishing their trust with an AutoML tool.

Artificial Intelligence (AI) can now automate the algorithm selection, feature engineering, and hyperparameter tuning steps in a machine learning workflow. Commonly known as AutoML or AutoAI, these technologies aim to relieve data scientists from the tedious manual work. However, today's AutoAI systems often present only limited to no information about the process of how they select and generate model results. Thus, users often do not understand the process, neither do they trust the outputs. In this short paper, we provide a first user evaluation by 10 data scientists of an experimental system, AutoAIViz, that aims to visualize AutoAI's model generation process. We find that the proposed system helps users to complete the data science tasks, and increases their understanding, toward the goal of increasing trust in the AutoAI system.

Text-based conversational systems, also referred to as chatbots, have grown widely popular. Current natural language understanding technologies are not yet ready to tackle the complexities in conversational interactions. Breakdowns are common, leading to negative user experiences. Guided by communication theories, we explore user preferences for eight repair strategies, including ones that are common in commercially-deployed chatbots (e.g., confirmation, providing options), as well as novel strategies that explain characteristics of the underlying machine learning algorithms. We conducted a scenario-based study to compare repair strategies with Mechanical Turk workers (N=203). We found that providing options and explanations were generally favored, as they manifest initiative from the chatbot and are actionable to recover from breakdowns. Through detailed analysis of participants' responses, we provide a nuanced understanding on the strengths and weaknesses of each repair strategy.

Quantum computing is a fundamentally different way of performing computation than classical computing. Many problems that are considered hard for classical computers may have efficient solutions using quantum computers. Recently, technology companies including IBM, Microsoft, and Google have invested in developing both quantum computing hardware and software to explore the potential of quantum computing. Because of the radical shift in computing paradigms that quantum represents, we see an opportunity to study the unique needs people have when interacting with quantum systems, what we call Quantum HCI (QHCI). Based on interviews with experts in quantum computing, we identify four areas in which HCI researchers can contribute to the field of quantum computing. These areas include understanding current and future quantum users, tools for programming and debugging quantum algorithms, visualizations of quantum states, and educational materials to train the first generation of "quantum native" programmers.

Chatbots are becoming quite popular, with many brands developing conversational experiences using platforms such as IBM's Watson Assistant and Facebook Messenger. However, previous research reveals that users' expectations of what conversational agents can understand and do far outpace their actual technical capabilities. Our work seeks to bridge the gap between these expectations and reality by designing a fun learning experience with several goals: explaining how chatbots work by mapping utterances to a set of intents, teaching strategies for avoiding conversational breakdowns, and increasing desire to use chatbots by creating feelings of empathy toward them. Our experience, called BigBlueBot, consists of interactions with two chatbots in which breakdowns occur and the user (or chatbot) must recover using one or more repair strategies. In a Mechanical Turk evaluation (N=88), participants learned strategies for having successful human-agent interactions, reported feelings of empathy toward the chatbots, and expressed a desire to interact with chatbots in the future.

The rapid advancement of artificial intelligence (AI) is changing our lives in many ways. One application domain is data science. New techniques in automating the creation of AI, known as AutoAI or AutoML, aim to automate the work practices of data scientists. AutoAI systems are capable of autonomously ingesting and pre-processing data, engineering new features, and creating and scoring models based on a target objectives (e.g. accuracy or run-time efficiency). Though not yet widely adopted, we are interested in understanding how AutoAI will impact the practice of data science. We conducted interviews with 20 data scientists who work at a large, multinational technology company and practice data science in various business settings. Our goal is to understand their current work practices and how these practices might change with AutoAI. Reactions were mixed: while informants expressed concerns about the trend of automating their jobs, they also strongly felt it was inevitable. Despite these concerns, they remained optimistic about their future job security due to a view that the future of data science work will be a collaboration between humans and AI systems, in which both automation and human expertise are indispensable.

Inertial sensors continuously track the 3D orientation of a flying drone, serving as the bedrock for maneuvers and stabilization. However, even the best inertial measurement units (IMU) are prone to various types of correlated failures. We consider using multiple GPS receivers on the drone as a fail-safe mechanism for IMU failures. The core challenge is in accurately computing the relative locations between each receiver pair, and translating these measurements into the drone's 3D orientation. Achieving IMU-like orientation requires the relative GPS distances to be accurate to a few centimeters -- a difficult task given that GPS today is only accurate to around 1-4 meters. Moreover, GPS-based orientation needs to be precise even under sharp drone maneuvers, GPS signal blockage, and sudden bouts of missing data. This paper designs SafetyNet, an off-the-shelf GPS-only system that addresses these challenges through a series of techniques, culminating in a novel particle filter framework running over multi-GNSS systems (GPS, GLONASS, and SBAS). Results from 11 sessions of 5-7 minute flights report median orientation accuracies of 2° even under overcast weather conditions. Of course, these improvements arise from an increase in cost due to the multiple GPS receivers, however, when safety is of interest, we believe that tradeoff is worthwhile.

In this paper, we present Expediting Expertise, a system designed to provide structured support to the otherwise informal process of social learning in the enterprise. It employs a data-driven approach where online content is automatically analyzed and categorized into relevant topics, topic-specific user expertise is calculated by comparing the models of individual users against those of the experts, and personalized recommendation of learning activities is created accordingly to facilitate expertise development. The system's UI is designed to provide users with ongoing feedback of current expertise, progress, and comparison with others. Learning recommendation is visualized with an interactive treemap which presents estimated return on investment and distance to current expertise for each recommended learning activity. Evaluation of the system showed very positive results.

Watching video online is becoming increasingly popular, and new video streaming technologies have the potential to transform video watching from a passive, isolating experience into an active, socially engaging experience. However, the viability of an active social experience is unclear: both chatting and watching video require attention, and may interfere with one another and detract from the experience. In this paper, we empirically examine the activity of chatting while watching video online. We examine how groups of friends and strangers interact, and find that chat has a positive influence on social relationships, and people chat despite being distracted. We discuss the benefits and opportunities provided by mixing chat and video, uncover some of the attentional and social challenges inherent in this combination of media, and provide guidance for structuring the viewing experience.

IBM Community Tools (ICT) is a synchronous broadcast messaging system in use by a very large, globally distributed organization. ICT is interesting for a number of reasons, including its scale of use (thousands of users per day), its usage model of employing large scale broadcast to strangers to initiate small group interactions, and the fact that it is a synchronous system used across multiple time zones. In this paper we characterize the use of ICT in its context, examine the activities for which it is used, the motivations of its users, and the values they derive from it. We also explore problems with the system, and look at the social and technical ways in which users deal with them.