As agentic AI systems grow increasingly capable of operating for hours or days at a time, users’ prompts are transforming into highly elaborate specifications for the AI to autonomously work on. While prompting for bounded, single-turn tasks has been extensively studied, less is known about how people communicate specifications for long-horizon tasks. In this work, we conducted a qualitative study in which 16 professionals drafted specifications for both a human colleague and an AI, revealing a core divergence: participants treated human delegation as a “compass,” offering high-level intent to encourage flexible exploration. In contrast, communication with AI resembled painstakingly laying down “railway tracks”: rigid, exhaustive instructions to minimize ambiguity and deviation. This reflected a perception that current AI struggles to infer intent, prioritize, and make judgments on its own. When envisioning an ideal AI collaborator, users expressed a desire for a hybrid : a collaborator blending AI’s efficiency and large context window with the critical thinking and agency of a human colleague. We discuss design implications for future AI systems, proposing that they align on outcomes through generated rough drafts, verify feasibility via end-to-end “test runs,” and monitor execution through intelligent check-ins—ultimately transforming AI from a passive instruction-follower into a reliable collaborator for ambiguous, long-horizon tasks.

In this work, we explore explicit Large Language Model (LLM)powered support for the iterative design of computer programs.Program design, like other design activity, is characterized by navigating a space of alternative problem formulations and associated solutions in an iterative fashion.LLMs are potentially powerful tools in helping this exploration; however, by default, code-generation LLMs deliver code that represents a particular point solution.This obscures the larger space of possible alternatives, many of which might be preferable to the LLM's default interpretation and its generated code.We contribute an IDE that supports program design through generating and showing new ways to frame problems alongside alternative solutions, tracking design decisions, and identifying implicit decisions made by either the programmer or the LLM.In a user study, we find that with our IDE, users combine and parallelize design phases to explore a broader design space-but also struggle to keep up with LLM-originated changes to code and other information overload.These findings suggest a core challenge for future IDEs that support program design through higher-level instructions given to LLM-based agents: carefully managing attention and deciding what information agents should surface to program designers and when.

Multimodal large language models (MLLMs), with their expansive world knowledge and reasoning capabilities, present a unique opportunity for end-users to create personalized AI sensors capable of reasoning about complex situations. A user could describe a desired sensing task in natural language (e.g., "alert if my toddler is getting into mischief"), with the MLLM analyzing the camera feed and responding within seconds. In a formative study, we found that users saw substantial value in defining their own sensors, yet struggled to articulate their unique personal requirements and debug the sensors through prompting alone. To address these challenges, we developed Gensors, a system that empowers users to define customized sensors supported by the reasoning capabilities of MLLMs. Gensors 1) assists users in eliciting requirements through both automatically-generated and manually created sensor criteria, 2) facilitates debugging by allowing users to isolate and test individual criteria in parallel, 3) suggests additional criteria based on user-provided images, and 4) proposes test cases to help users "stress test" sensors on potentially unforeseen scenarios. In a user study, participants reported significantly greater sense of control, understanding, and ease of communication when defining sensors using Gensors. Beyond addressing model limitations, Gensors supported users in debugging, eliciting requirements, and expressing unique personal requirements to the sensor through criteria-based reasoning; it also helped uncover users' "blind spots" by exposing overlooked criteria and revealing unanticipated failure modes. Finally, we discuss how unique characteristics of MLLMs--such as hallucinations and inconsistent responses--can impact the sensor-creation process. These findings contribute to the design of future intelligent sensing systems that are intuitive and customizable by everyday users.

Recent advances in general-purpose AI underscore the urgent need to align AI systems with human goals and values. Yet, the lack of a clear, shared understanding of what constitutes "alignment" limits meaningful progress and cross-disciplinary collaboration. In this position paper, we argue that the research community should explicitly define and critically reflect on "alignment" to account for the bidirectional and dynamic relationship between humans and AI. Through a systematic review of over 400 papers spanning HCI, NLP, ML, and more, we examine how alignment is currently defined and operationalized. Building on this analysis, we introduce the Bidirectional Human-AI Alignment framework, which not only incorporates traditional efforts to align AI with human values but also introduces the critical, underexplored dimension of aligning humans with AI – supporting cognitive, behavioral, and societal adaptation to rapidly advancing AI technologies. Our findings reveal significant gaps in current literature, especially in long-term interaction design, human value modeling, and mutual understanding. We conclude with three central challenges and actionable recommendations to guide future research toward more nuanced, reciprocal, and human-AI alignment approaches.

Evaluating large language models (LLMs) presents unique challenges. While automatic side-by-side evaluation, also known as LLM-as-a-judge, has become a promising solution, model developers and researchers face difficulties with scalability and interpretability when analyzing these evaluation outcomes. To address these challenges, we introduce LLM Comparator, a new visual analytics tool designed for side-by-side evaluations of LLMs. This tool provides analytical workflows that help users understand when and why one LLM outperforms or underperforms another, and how their responses differ. Through close collaboration with practitioners developing LLMs at Google, we have iteratively designed, developed, and refined the tool. Qualitative feedback from these users highlights that the tool facilitates in-depth analysis of individual examples while enabling users to visually overview and flexibly slice data. This empowers users to identify undesirable patterns, formulate hypotheses about model behavior, and gain insights for model improvement. LLM Comparator has been integrated into Google's LLM evaluation platforms and open-sourced.

Prototyping AI applications is notoriously difficult. While large language model (LLM) prompting has dramatically lowered the barriers to AI prototyping, designers are still prototyping AI functionality and UI separately. We investigate how coupling prompt and UI design affects designers’ workflows. Grounding this research, we developed PromptInfuser, a Figma plugin that enables users to create semi-functional mockups, by connecting UI elements to the inputs and outputs of prompts. In a study with 14 designers, we compare PromptInfuser to designers’ current AI-prototyping workflow. PromptInfuser was perceived to be significantly more useful for communicating product ideas, more capable of producing prototypes that realistically represent the envisioned artifact, more efficient for prototyping, and more helpful for anticipating UI issues and technical constraints. PromptInfuser encouraged iteration over prompt and UI together, which helped designers identify UI and prompt incompatibilities and reflect upon their total solution. Together, these findings inform future systems for prototyping AI applications.

Prompt-based interfaces for Large Language Models (LLMs) have made prototyping and building AI-powered applications easier than ever before. However, identifying potential harms that may arise from AI applications remains a challenge, particularly during prompt-based prototyping. To address this, we present Farsight, a novel in situ interactive tool that helps people identify potential harms from the AI applications they are prototyping. Based on a user’s prompt, Farsight highlights news articles about relevant AI incidents and allows users to explore and edit LLM-generated use cases, stakeholders, and harms. We report design insights from a co-design study with 10 AI prototypers and findings from a user study with 42 AI prototypers. After using Farsight, AI prototypers in our user study are better able to independently identify potential harms associated with a prompt and find our tool more useful and usable than existing resources. Their qualitative feedback also highlights that Farsight encourages them to focus on end-users and think beyond immediate harms. We discuss these findings and reflect on their implications for designing AI prototyping experiences that meaningfully engage with AI harms. Farsight is publicly accessible at: https://pair-code.github.io/farsight.

Large language model (LLM) prompting is a promising new approach for users to create and customize their own chatbots. However, current methods for steering a chatbot’s outputs, such as prompt engineering and fine-tuning, do not support users in converting their natural feedback on the model’s outputs to changes in the prompt or model. In this work, we explore how to enable users to interactively refine model outputs through their feedback, by helping them convert their feedback into a set of principles (i.e. a constitution) that dictate the model’s behavior. From a formative study, we (1) found that users needed support converting their feedback into principles for the chatbot and (2) classified the different principle types desired by users. Inspired by these findings, we developed ConstitutionMaker, an interactive tool for converting user feedback into principles, to steer LLM-based chatbots. With ConstitutionMaker, users can provide either positive or negative feedback in natural language, select auto-generated feedback, or rewrite the chatbot’s response; each mode of feedback automatically generates a principle that is inserted into the chatbot’s prompt. In a user study with 14 participants, we compare ConstitutionMaker to an ablated version, where users write their own principles. With ConstitutionMaker, participants felt that their principles could better guide the chatbot, that they could more easily convert their feedback into principles, and that they could write principles more efficiently, with less mental demand. ConstitutionMaker helped users identify ways to improve the chatbot, formulate their intuitive responses to the model into feedback, and convert this feedback into specific and clear principles. Together, these findings inform future tools that support the interactive critiquing of LLM outputs.

Recent advances in multimodal large language models (LLMs) have made it easier to rapidly prototype AI-powered features, especially for mobile use cases. However, gathering early, mobile-situated user feedback on these AI prototypes remains challenging. The broad scope and flexibility of LLMs means that, for a given use-case-specific prototype, there is a crucial need to understand the wide range of in-the-wild input users are likely to provide and their in-context expectations for the AI’s behavior. To explore the concept of in situ AI prototyping and testing, we created MobileMaker: a platform that enables designers to rapidly create and test mobile AI prototypes directly on devices. This tool also enables testers to make on-device, in-the-field revisions of prototypes using natural language. In an exploratory study with 16 participants, we explored how user feedback on prototypes created with MobileMaker compares to that of existing prototyping tools (e.g., Figma, prompt editors). Our findings suggest that MobileMaker prototypes enabled more serendipitous discovery of: model input edge cases, discrepancies between AI’s and user’s in-context interpretation of the task, and contextual signals missed by the AI. Furthermore, we learned that while the ability to make in-the-wild revisions led users to feel more fulfilled as active participants in the design process, it might also constrain their feedback to the subset of changes perceived as more actionable or implementable by the prototyping tool.

OBJECTIVE: To evaluate the real-world performance of the SMART/HL7 Bulk Fast Health Interoperability Resources (FHIR) Access Application Programming Interface (API), developed to enable push button access to electronic health record data on large populations, and required under the 21st Century Cures Act Rule. MATERIALS AND METHODS: We used an open-source Bulk FHIR Testing Suite at 5 healthcare sites from April to September 2023, including 4 hospitals using electronic health records (EHRs) certified for interoperability, and 1 Health Information Exchange (HIE) using a custom, standards-compliant API build. We measured export speeds, data sizes, and completeness across 6 types of FHIR. RESULTS: Among the certified platforms, Oracle Cerner led in speed, managing 5-16 million resources at over 8000 resources/min. Three Epic sites exported a FHIR data subset, achieving 1-12 million resources at 1555-2500 resources/min. Notably, the HIE's custom API outperformed, generating over 141 million resources at 12 000 resources/min. DISCUSSION: The HIE's custom API showcased superior performance, endorsing the effectiveness of SMART/HL7 Bulk FHIR in enabling large-scale data exchange while underlining the need for optimization in existing EHR platforms. Agility and scalability are essential for diverse health, research, and public health use cases. CONCLUSION: To fully realize the interoperability goals of the 21st Century Cures Act, addressing the performance limitations of Bulk FHIR API is critical. It would be beneficial to include performance metrics in both certification and reporting processes.

OBJECTIVE: To address challenges in large-scale electronic health record (EHR) data exchange, we sought to develop, deploy, and test an open source, cloud-hosted app "listener" that accesses standardized data across the SMART/HL7 Bulk FHIR Access application programming interface (API). METHODS: We advance a model for scalable, federated, data sharing and learning. Cumulus software is designed to address key technology and policy desiderata including local utility, control, and administrative simplicity as well as privacy preservation during robust data sharing, and artificial intelligence (AI) for processing unstructured text. RESULTS: Cumulus relies on containerized, cloud-hosted software, installed within a healthcare organization's security envelope. Cumulus accesses EHR data via the Bulk FHIR interface and streamlines automated processing and sharing. The modular design enables use of the latest AI and natural language processing tools and supports provider autonomy and administrative simplicity. In an initial test, Cumulus was deployed across 5 healthcare systems each partnered with public health. Cumulus output is patient counts which were aggregated into a table stratifying variables of interest to enable population health studies. All code is available open source. A policy stipulating that only aggregate data leave the institution greatly facilitated data sharing agreements. DISCUSSION AND CONCLUSION: Cumulus addresses barriers to data sharing based on (1) federally required support for standard APIs, (2) increasing use of cloud computing, and (3) advances in AI. There is potential for scalability to support learning across myriad network configurations and use cases.

This paper examines the art practices, artwork, and motivations of prolific users of the latest generation of text-to-image models. Through interviews, observations, and a user survey, we present a sampling of the artistic styles and describe the developed community of practice around generative AI. We find that: 1) artists hold the text prompt and the resulting image can be considered collectively as a form of artistic expression (prompts as art), and 2) prompt templates (prompts with “slots” for others to fill in with their own words) are developed to create generative art styles. We discover that the value placed by this community on unique outputs leads to artists seeking specialized vocabulary to produce distinctive art pieces (e.g., by reading architectural blogs to find phrases to describe images). We also find that some artists use “glitches” in the model that can be turned into artistic styles of their own right. From these findings, we outline specific implications for design regarding future prompting and image editing options.

Users of augmentative and alternative communication (AAC) devices sometimes find it difficult to communicate in real time with others due to the time it takes to compose messages. AI technologies such as large language models (LLMs) provide an opportunity to support AAC users by improving the quality and variety of text suggestions. However, these technologies may fundamentally change how users interact with AAC devices as users transition from typing their own phrases to prompting and selecting AI-generated phrases. We conducted a study in which 12 AAC users tested live suggestions from a language model across three usage scenarios: extending short replies, answering biographical questions, and requesting assistance. Our study participants believed that AI-generated phrases could save time, physical and cognitive effort when communicating, but felt it was important that these phrases reflect their own communication style and preferences. This work identifies opportunities and challenges for future AI-enhanced AAC devices.

Technology companies continue to invest in efforts to incorporate responsibility in their Artificial Intelligence (AI) advancements, while efforts to audit and regulate AI systems expand. This shift towards Responsible AI (RAI) in the tech industry necessitates new practices and adaptations to roles—undertaken by a variety of practitioners in more or less formal positions, many of whom focus on the user-centered aspects of AI. To better understand practices at the intersection of user experience (UX) and RAI, we conducted an interview study with industrial UX practitioners and RAI subject matter experts, both of whom are actively involved in addressing RAI concerns throughout the early design and development of new AI-based prototypes, demos, and products, at a large technology company. Many of the specific practices and their associated challenges have yet to be surfaced in the literature, and distilling them offers a critical view into how practitioners’ roles are adapting to meet present-day RAI challenges. We present and discuss three emerging practices in which RAI is being enacted and reified in UX practitioners’ everyday work. We conclude by arguing that the emerging practices, goals, and types of expertise that surfaced in our study point to an evolution in praxis, with associated challenges that suggest important areas for further research in HCI.

In this paper, we present a natural language code synthesis tool, GenLine, backed by 1) a large generative language model and 2) a set of task-specific prompts that create or change code. To understand the user experience of natural language code synthesis with these new types of models, we conducted a user study in which participants applied GenLine to two programming tasks. Our results indicate that while natural language code synthesis can sometimes provide a magical experience, participants still faced challenges. In particular, participants felt that they needed to learn the model’s “syntax,” despite their input being natural language. Participants also struggled to form an accurate mental model of the types of requests the model can reliably translate and developed a set of strategies to debug model input. From these findings, we discuss design implications for future natural language code synthesis tools built using large generative language models.

Although large language models (LLMs) have demonstrated impressive potential on simple tasks, their breadth of scope, lack of transparency, and insufficient controllability can make them less effective when assisting humans on more complex tasks. In response, we introduce the concept of Chaining LLM steps together, where the output of one step becomes the input for the next, thus aggregating the gains per step. We first define a set of LLM primitive operations useful for Chain construction, then present an interactive system where users can modify these Chains, along with their intermediate results, in a modular way. In a 20-person user study, we found that Chaining not only improved the quality of task outcomes, but also significantly enhanced system transparency, controllability, and sense of collaboration. Additionally, we saw that users developed new ways of interacting with LLMs through Chains: they leveraged sub-tasks to calibrate model expectations, compared and contrasted alternative strategies by observing parallel downstream effects, and debugged unexpected model outputs by “unit-testing” sub-components of a Chain. In two case studies, we further explore how LLM Chains may be used in future applications.

This paper describes results from a study examining how musicians have been affected by the restrictive environments imposed by the COVID-19 pandemic, and the corresponding technological implications. Through a survey of 29 musicians and additional interviews with 7 professional improvisation musicians, we observe the challenges musicians face in 1) finding the technological infrastructure and shared spaces necessary for dynamic, remote creative collaborations, 2) producing the mindset, free time, and sources of inspiration necessary for initiating creativity during times of stress, and 3) maintaining (and potentially expanding) the social connections and creative community vital to creative practice. We also report on how some musicians have creatively leveraged the radical changes in their lives to drive new artistic practices and styles of music. Collectively, these data illustrate the resilience of certain existing remote collaboration and creative tools, while suggesting ways other digital tools could more flexibly accommodate new use cases. The data also suggest the value of tools and services that help people creatively cope with radical changes to their lives and livelihoods.

Recent advances in deep generative neural networks have made it possible for artificial intelligence to actively collaborate with human beings in co-creating novel content (e.g. music, art). While substantial research focuses on (individual) human-AI collaborations, comparatively less research examines how AI can play a role in human-human collaborations during co-creation. In a qualitative lab study, we observed 30 participants (15 pairs) compose a musical phrase in pairs, both with and without AI. Our findings reveal that AI may play important roles in influencing human social dynamics during creativity, including: 1) implicitly seeding a common ground at the start of collaboration, 2) acting as a psychological safety net in creative risk-taking, 3) providing a force for group progress, 4) mitigating interpersonal stalling and friction, and 5) altering users’ collaborative and creative roles. This work contributes to the future of generative AI in social creativity by providing implications for how AI could enrich, impede, or alter creative social dynamics in the years to come.

Integrated Gradients (IG) [29] is a commonly used feature attribution method for deep neural networks. While IG has many desirable properties, the method often produces spurious/noisy pixel attributions in regions that are not related to the predicted class when applied to visual models. While this has been previously noted [27], most existing solutions [25], [17] are aimed at addressing the symptoms by explicitly reducing the noise in the resulting attributions. In this work, we show that one of the causes of the problem is the accumulation of noise along the IG path. To minimize the effect of this source of noise, we propose adapting the attribution path itself - conditioning the path not just on the image but also on the model being explained. We introduce Adaptive Path Methods (APMs) as a generalization of path methods, and Guided IG as a specific instance of an APM. Empirically, Guided IG creates saliency maps better aligned with the model's prediction and the input image that is being explained. We show through qualitative and quantitative experiments that Guided IG outperforms other, related methods in nearly every experiment.

While generative deep neural networks (DNNs) have demonstrated their capacity for creating novel musical compositions, less attention has been paid to the challenges and potential of co-creating with these musical AIs, especially for novices. In a needfinding study with a widely used, interactive musical AI, we found that the AI can overwhelm users with the amount of musical content it generates, and frustrate them with its non-deterministic output. To better match co-creation needs, we developed AI-steering tools, consisting of Voice Lanes that restrict content generation to particular voices; Example-Based Sliders to control the similarity of generated content to an existing example; Semantic Sliders to nudge music generation in high-level directions (happy/sad, conventional/surprising); and Multiple Alternatives of generated content to audition and choose from. In a summative study (N=21), we discovered the tools not only increased users' trust, control, comprehension, and sense of collaboration with the AI, but also contributed to a greater sense of self-efficacy and ownership of the composition relative to the AI.

Machine learning (ML) is increasingly being used in image retrieval systems for medical decision making. One application of ML is to retrieve visually similar medical images from past patients (e.g. tissue from biopsies) to reference when making a medical decision with a new patient. However, no algorithm can perfectly capture an expert's ideal notion of similarity for every case: an image that is algorithmically determined to be similar may not be medically relevant to a doctor's specific diagnostic needs. In this paper, we identified the needs of pathologists when searching for similar images retrieved using a deep learning algorithm, and developed tools that empower users to cope with the search algorithm on-the-fly, communicating what types of similarity are most important at different moments in time. In two evaluations with pathologists, we found that these tools increased the diagnostic utility of images found and increased user trust in the algorithm. The tools were preferred over a traditional interface, without a loss in diagnostic accuracy. We also observed that users adopted new strategies when using refinement tools, re-purposing them to test and understand the underlying algorithm and to disambiguate ML errors from their own errors. Taken together, these findings inform future human-ML collaborative systems for expert decision-making.

Saliency methods can aid understanding of deep neural networks. Recent years have witnessed many improvements to saliency methods, as well as new ways for evaluating them. In this paper, we 1) present a novel region-based attribution method, XRAI, that builds upon integrated gradients (Sundararajan et al. 2017), 2) introduce evaluation methods for empirically assessing the quality of image-based saliency maps (Performance Information Curves (PICs)), and 3) contribute an axiom-based sanity check for attribution methods. Through empirical experiments and example results, we show that XRAI produces better results than other saliency methods for common models and the ImageNet dataset.

Although rapid advances in machine learning have made it increasingly applicable to expert decision-making, the delivery of accurate algorithmic predictions alone is insufficient for effective human-AI collaboration. In this work, we investigate the key types of information medical experts desire when they are first introduced to a diagnostic AI assistant. In a qualitative lab study, we interviewed 21 pathologists before, during, and after being presented deep neural network (DNN) predictions for prostate cancer diagnosis, to learn the types of information that they desired about the AI assistant. Our findings reveal that, far beyond understanding the local, case-specific reasoning behind any model decision, clinicians desired upfront information about basic, global properties of the model, such as its known strengths and limitations, its subjective point-of-view, and its overall design objective--what it's designed to be optimized for. Participants compared these information needs to the collaborative mental models they develop of their medical colleagues when seeking a second opinion: the medical perspectives and standards that those colleagues embody, and the compatibility of those perspectives with their own diagnostic patterns. These findings broaden and enrich discussions surrounding AI transparency for collaborative decision-making, providing a richer understanding of what experts find important in their introduction to AI assistants before integrating them into routine practice.

We present GEM-NI -- a graph-based generative-design tool that supports parallel exploration of alternative designs. Producing alternatives is a key feature of creative work, yet it is not strongly supported in most extant tools. GEM-NI enables various forms of exploration with alternatives such as parallel editing, recalling history, branching, merging, comparing, and Cartesian products of and for alternatives. Further, GEM-NI provides a modal graphical user interface and a design gallery, which both allow designers to control and manage their design exploration. We conducted an exploratory user study followed by in-depth one-on-one interviews with moderately and highly skills participants and obtained positive feedback for the system features, showing that GEM-NI supports creative design work well.

Mobile advertising is a rapidly growing form of advertising, carrying with it the promise of more finely tuned, targeted advertisements. In this paper, we study mobile advertising in the use of public transportation (specifically, buses). Through a qualitative study, we identify a number of factors that can influence the effectiveness of mobile advertising for bus passengers. We then use these findings to inform a prototype advertising system for bus passengers, called Bus Mate. Collectively, our research suggests that the bus passenger's trip timeline (i.e., How long they will be on the bus, and where they are on the trip) is one of the most important factors in defining the users' attention level. We propose an attention graph and validate it using our experimental mobile application. Finally, we propose some design recommendations, based on our findings, for platforms aiming at targeting mobile ads to bus passengers.

Manipulated images lose believability if the user's edits fail to account for shadows. We propose a method that makes removal and editing of soft shadows easy. Soft shadows are ubiquitous, but remain notoriously difficult to extract and manipulate. We posit that soft shadows can be segmented, and therefore edited, by learning a mapping function for image patches that generates shadow mattes. We validate this premise by removing soft shadows from photographs with only a small amount of user input. Given only broad user brush strokes that indicate the region to be processed, our new supervised regression algorithm automatically unshadows an image, removing the umbra and penumbra. The resulting lit image is frequently perceived as a believable shadow-free version of the scene. We tested the approach on a large set of soft shadow images, and performed a user study that compared our method to the state-of-the-art and to real lit scenes. Our results are more difficult to identify as being altered and are perceived as preferable compared to prior work.

Technology drives advances in science. Giving scientists access to more powerful tools for collecting and understanding data enables them to both ask and answer new kinds questions that were previously beyond their reach. Of these new tools at their disposal, machine learning offers the opportunity to understand and analyze data at unprecedented scales and levels of detail. The standard machine learning pipeline consists of data labeling, feature extraction, training, and evaluation. However, without expert machine learning knowledge, it is difficult for scientists to optimally construct this pipeline to fully leverage machine learning in their work. Using ecology as a motivating example, we analyze a typical scientist's data collection and processing workflow and highlight many problems facing practitioners when attempting to capitalize on advances in machine learning and pattern recognition. Understanding these shortcomings allows us to outline several novel and underexplored research directions. We end with recommendations to motivate progress in future cross-disciplinary work.