product design teams

Abstract: Text-to-image (T2I) models are typically evaluated for bias using slot-based templates such as ``a photo of a [profession]''. Such templates probe only \emph{explicit} demographic attributes (e.g., gender, skin tone) in isolation. They overlook a broader \emph{implicit} bias that arises in natural prompts: when stereotype-relevant attributes are left unspecified, models still default to stereotypical outputs. We introduce IMPLICIT-Bench, a benchmark for measuring implicit bias in T2I models under such prompts. The key design is a structured-knowledge-graph (KG) construction of controlled prompt triplets: neutral, stereotype, and anti-stereotype variants that differ only along a single bias dimension while preserving scene semantics. This enables precise attribution of bias effects that template benchmarks cannot achieve. IMPLICIT-Bench comprises 5,493 prompts across 11 bias categories, validated through multi-model agreement, CLIP-based verification, and human evaluation. Using this benchmark, we show that state-of-the-art T2I models exhibit systematic bias under neutral prompts, a failure mode largely invisible to existing evaluations. We then use IMPLICIT-Bench to evaluate debiasing methods, uncovering a fundamental trade-off between bias reduction and semantic fidelity.

Abstract: Doing inclusive design in HCI practice can be labor-intensive, a costly barrier that some companies and HCI practitioners may be unwilling or unable to overcome. Yet, not doing inclusive design is costly too, in the form of UX barriers that disproportionately disadvantage under-served user populations. To address this problem, we introduce Apply-<x>Mag, an LLM-powered tool to support HCI practitioners' work to design their products inclusively to wide ranges of users. Apply-<x>Mag is general, supporting any inclusive design method that can be expressed as <x>Mags (i.e., using attribute ranges and heuristics). It is also effective: Empirical results with researcher and practitioner teams using various combinations of two <x>Mags on 7 products showed Apply-<x>Mag precision averaging 90-99% and recall averaging 82-89%. Further, its environmental costs were reasonable, costing about the same resources as 2-4 ordinary Google searches.

Abstract: The mental model construct is widely used in HCI to refer to the knowledge structure people hold in order to reason about and interact with computing systems. Yet it is often operationalized intuitively: the construct is often used interchangeably with related concepts (e.g., folk theories, sensemaking) and methods of studying it (e.g., through elicitation) are many and diverse, with each method resting on distinct assumptions about what counts as a mental model. Generative and agentic AI systems may further complicate mental model formation and elicitation as such systems are opaque by design and increasingly act on users' behalf across files, applications, and on the web. Together, these challenges may hinder the commensurability of research on people's mental models of AI systems. The MM/AI workshop calls for a critical reassessment of how we understand and study mental models in human-AI interaction research. It aims to foster theoretical and methodological exchange on mental models in human-AI interaction, identify open challenges, and develop directions for future research. We invite short papers on users' or stakeholders' mental models of AI systems, particularly contributions that reflect on the conceptual and methodological foundations of the construct. The half-day workshop combines lightning talks, hands-on elicitation exercises, and structured discussions on key questions concerning the future of the mental model for human-AI interaction research.