Interactive Model Cards: A Human-Centered Approach to Model Documentation

TLDR

Deep learning NLP models are increasingly used by analysts without formal ML training, yet existing documentation is tailored to experts. The study seeks to create interactive model cards that enable non‑experts to explore and understand model documentation. We conducted a design inquiry comprising a conceptual study with ML, NLP, and AI‑ethics experts and an evaluative study with 30 non‑expert analysts, gathering semi‑structured interview data and performing thematic analysis to identify key design dimensions. The results highlight that thoughtful interactivity and design—such as clear language, visual cues, and warnings—are essential for orienting non‑experts, and we distill these insights into guidelines for human‑centered AI/ML documentation.

Abstract

Deep learning models for natural language processing (NLP) are increasingly adopted and deployed by analysts without formal training in NLP or machine learning (ML). However, the documentation intended to convey the model's details and appropriate use is tailored primarily to individuals with ML or NLP expertise. To address this gap, we conduct a design inquiry into interactive model cards, which augment traditionally static model cards with affordances for exploring model documentation and interacting with the models themselves. Our investigation consists of an initial conceptual study with experts in ML, NLP, and AI Ethics, followed by a separate evaluative study with non-expert analysts who use ML models in their work. Using a semi-structured interview format coupled with a think-aloud protocol, we collected feedback from a total of 30 participants who engaged with different versions of standard and interactive model cards. Through a thematic analysis of the collected data, we identified several conceptual dimensions that summarize the strengths and limitations of standard and interactive model cards, including: stakeholders; design; guidance; understandability & interpretability; sensemaking & skepticism; and trust & safety. Our findings demonstrate the importance of carefully considered design and interactivity for orienting and supporting non-expert analysts using deep learning models, along with a need for consideration of broader sociotechnical contexts and organizational dynamics. We have also identified design elements, such as language, visual cues, and warnings, among others, that support interactivity and make non-interactive content accessible. We summarize our findings as design guidelines and discuss their implications for a human-centered approach towards AI/ML documentation.