Human-in-the-loop optimization identifies optimal interface designs by iteratively observing user performance. However, it often requires numerous iterations due to the lack of prior information. While recent approaches have accelerated this process by leveraging previous optimization data, collecting user data remains costly and often impractical. We present a conceptual framework, Human-in-the-Loop Optimization with Model-Informed Priors (HOMI), which augments human-in-the-loop optimization with a training phase where the optimizer learns adaptation strategies from diverse, synthetic user data generated with predictive models before deployment. To realize HOMI, we introduce Neural Acquisition Function+ (NAF+), a Bayesian optimization method featuring a neural acquisition function trained with reinforcement learning. NAF+ learns optimization strategies from large-scale synthetic data, improving efficiency in real-time optimization with users. We evaluate HOMI and NAF+ with mid-air keyboard optimization, a representative VR input task. Our work presents a new approach for more efficient interface adaptation by bridging in situ and in silico optimization processes.
Information systems, such as electronic health records (EHRs) and case note software, increasingly support direct service providers (DSPs) in social service administration. Previous scholarship examined how these digital interventions enhance care but also create unintended consequences for DSPs and their clients. Despite broad interest in how DSPs and other frontline social service workers utilize information technology, few studies examine how they avoid digital tools, particularly when documentation stakes are high for both clients and DSPs. We report findings from interviews with 16 DSPs, who remain keenly aware that the information they document may become visible to others now and in the future. To protect themselves and their clients, they develop practices to resist recording data in digital records such as EHRs. We offer a typology of resistant data practices and design considerations grounded in the experiences and understanding of power within the roles of DSPs.
AI systems depend on the invisible and undervalued labor of data workers, who are often treated as interchangeable units rather than collaborators with meaningful expertise. Critical scholars and practitioners have proposed alternative principles for data work, but few empirical studies examine how to enact them in practice. This paper bridges this gap through a case study of multilingual, iterative, and participatory data annotation processes with journalists and activists focused on news narratives of gender-related violence. We offer two methodological contributions. First, we demonstrate how workshops rooted in feminist epistemology can foster dialogue, build community, and disrupt knowledge hierarchies in data annotation. Second, drawing insights from practice, we deepen analysis of existing feminist and participatory principles. We show that prioritizing context and pluralism in practice may require "bounding" context and working towards what we describe as a "tactical consensus.'' We also explore tensions around materially acknowledging labor while resisting transactional researcher-participant dynamics. Through this work, we contribute to growing efforts to reimagine data and AI development as relational and political spaces for understanding difference, enacting care, and building solidarity across shared struggles.
Peer-run organizations (PROs) provide critical, recovery-based behavioral health support rooted in lived experience. As large language models (LLMs) enter this domain, their scale, conversationality, and opacity introduce new challenges for situatedness, trust, and autonomy. Partnering with Collaborative Support Programs of New Jersey (CSPNJ), a statewide PRO in the Northeastern United States, we used comicboarding, a co-design method, to conduct workshops with 16 peer specialists and 10 service users exploring perceptions of integrating an LLM-based recommendation system into peer support. Findings show that depending on how LLMs are introduced, constrained, and co-used, they can reconfigure in-room dynamics by sustaining, undermining, or amplifying the relational authority that grounds peer support. We identify opportunities, risks, and mitigation strategies across three tensions: bridging scale and locality, protecting trust and relational dynamics, and preserving peer autonomy amid efficiency gains. We contribute design implications that center lived-experience-in-the-loop, reframe trust as co-constructed, and position LLMs not as clinical tools but as relational collaborators in high-stakes, community-led care.
To broaden participation in computing and AI design, researchers urge supporting individuals to probe datasets for biases that technologies might amplify. Critically probing data requires first recognizing that it is not neutral, achievable through data contextualization---understanding data contexts including its origin and contents to recognize opportunities or shortcomings. We created a web-tool, “Contextualizing Datasets”, that helps users contextualize data by guiding them in data exploration and different stakeholder interactions. We applied this to an educational case study---using 311 data for allocating government flood resources---with a graduate class. Our findings suggest the tool helped scaffold students in contextualizing data to critically question data curation methods and stakeholder representation, with the local case study context supporting them to draw from lived experiences. From our results, we share ways to improve and re-purpose Contextualizing Datasets and reflect over how it can be leveraged to address generative AI concerns.
AI capabilities for document reader software are usually presented in separate chat interfaces. We explore integrating AI into document comments, a concept we formalize as AI margin notes. Three design parameters characterize this approach: margin notes are integrated with the text while chat interfaces are not; selecting text for a margin note can be automated through AI or manual; and the generation of a margin note can involve AI to various degrees. Two experiments investigate integration and selection automation, with results showing participants prefer integrated AI margin notes and manual selection. A third experiment explores human and AI involvement through six alternative techniques. Techniques with less AI involvement resulted in more psychological ownership, but faster and less effortful designs were generally preferred. Surprisingly, the degree of AI involvement had no measurable effect on reading comprehension. Our work shows that AI margin notes are desirable and contributes implications for their design.
Dataset documentation is widely recognized as essential for the responsible development of automated systems. Despite growing efforts to support documentation through different kinds of artifacts, little is known about the motivations shaping documentation tool design or the factors hindering their adoption. We present a systematic review supported by mixed-methods analysis of 59 dataset documentation publications to examine the motivations behind building documentation tools, how authors conceptualize documentation practices, and how these tools connect to existing systems, regulations, and cultural norms. Our analysis shows four persistent patterns in dataset documentation conceptualization that potentially impede adoption and standardization: unclear operationalizations of documentation’s value, decontextualized designs, unaddressed labor demands, and a tendency to treat integration as future work. Building on these findings, we propose a shift in Responsible AI tool design toward institutional rather than individual solutions, and outline actions the HCI community can take to enable sustainable documentation practices.