Designing Beyond Language: Sociotechnical Barriers in AI Health Technologies for Limited English Proficiency
Not on the map. Why?
Abstract (arXiv)
Limited English proficiency (LEP) patients in the U.S. face systemic barriers to healthcare beyond language and interpreter access, encompassing procedural and institutional constraints. AI advances may support communication and care through on-demand translation and visit preparation, but also risk exacerbating existing inequalities. We conducted storyboard-driven interviews with 14 patient navigators to explore how AI could shape care experiences for Spanish-speaking LEP individuals. We identified tensions around linguistic and cultural misunderstandings, privacy concerns, and opportunities and risks for AI to augment care workflows. Participants highlighted structural factors that can undermine trust in AI systems, including sensitive information disclosure, unstable technology access, and low literacy. While AI tools can potentially alleviate social barriers and institutional constraints, there are risks of misinformation and reducing human-to-human interactions. Our findings contribute AI design considerations that support LEP patients and care teams via rapport-building, educational and language support, and minimizing disruptions to existing practices.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 39 of its 176 references that are in the map. First posted on arXiv 10 Nov 2025.
Builds on
39 of 176 references.
References · 39
- 2023QLoRA: Efficient Finetuning of Quantized LLMscited by 3,418
- 2025gpt-oss-120b & gpt-oss-20b Model Cardcited by 1,386
- 2023Voicebox: Text-Guided Multilingual Universal Speech Generation at Scalecited by 379
- 2024A Roadmap to Pluralistic Alignmentcited by 184
- 2023AI Transparency in the Age of LLMs: A Human-Centered Research Roadmapcited by 123
- 2021A Recipe For Arbitrary Text Style Transfer with Large Language Modelscited by 107
- 2013A Computational Approach to Politeness with Application to Social Factorscited by 106
- 2023Aligning Language Models to User Opinionscited by 99
- 2023NLPositionality: Characterizing Design Biases of Datasets and Modelscited by 94
- 2023Better to Ask in English: Cross-Lingual Evaluation of Large Language Models for Healthcare Queriescited by 82
- 2024Aligning LLMs with Individual Preferences via Interactioncited by 63
- 2020Automated Lay Language Summarization of Biomedical Scientific Reviewscited by 46
27 more
- 2025Creating General User Models from Computer Usecited by 44
- 2025Magentic-UI: Towards Human-in-the-loop Agentic Systemscited by 43
- 2025CowPilot: A Framework for Autonomous and Human-Agent Collaborative Web Navigationcited by 36
- 2024Few-shot Personalization of LLMs with Mis-aligned Responsescited by 32
- 2022Paper Plain: Making Medical Research Papers Approachable to Healthcare Consumers with Natural Language Processingcited by 23
- 2025BenchMAX: A Comprehensive Multilingual Evaluation Suite for Large Language Modelscited by 23
- 2023Physician Detection of Clinical Harm in Machine Translation: Quality Estimation Aids in Reliance and Backtranslation Identifies Critical Errorscited by 22
- 2023Modeling Cross-Cultural Pragmatic Inference with Codenames Duetcited by 20
- 2023The impact of generative artificial intelligence on socioeconomic inequalities and policy makingcited by 20
- 2024ValueCompass: A Framework for Measuring Contextual Value Alignment Between Human and LLMscited by 20
- 2023NLP for Maternal Healthcare: Perspectives and Guiding Principles in the Age of LLMscited by 14
- 2024User-Driven Value Alignment: Understanding Users' Perceptions and Strategies for Addressing Biased and Discriminatory Statements in AI Companionscited by 14
- 2023Sensing Wellbeing in the Workplace, Why and For Whom? Envisioning Impacts with Organizational Stakeholderscited by 13
- 2025AI Chatbots for Mental Health: Values and Harms from Lived Experiences of Depressioncited by 13
- 2025Mapping Caregiver Needs to AI Chatbot Design: Strengths and Gaps in Mental Health Support for Alzheimer's and Dementia Caregiverscited by 13
- 2024Human-Centered Privacy Research in the Age of Large Language Modelscited by 9
- 2024Targeted Multilingual Adaptation for Low-resource Language Familiescited by 9
- 2025Not Like Us, Hunty: Measuring Perceptions and Behavioral Effects of Minoritized Anthropomorphic Cues in LLMscited by 9
- 2025"Kya family planning after marriage hoti hai?": Integrating Cultural Sensitivity in an LLM Chatbot for Reproductive Healthcited by 5
- 2021Regionalized models for Spanish language variations based on Twittercited by 4
- 2025Knowledge Workers' Perspectives on AI Training for Responsible AI Usecited by 4
- 2025It's the same but not the same: Do LLMs distinguish Spanish varieties?cited by 3
- 2025EduAdapt: A Question Answer Benchmark Dataset for Evaluating Grade-Level Adaptability in LLMscited by 3
- 2025La Leaderboard: A Large Language Model Leaderboard for Spanish Varieties and Languages of Spain and Latin Americacited by 2
- 2024ProxyGPT: Enabling User Anonymity in LLM Chatbots via (Un)Trustworthy Volunteer Proxiescited by 1
- 2025Crossing Borders Without Crossing Boundaries: How Sociolinguistic Awareness Can Optimize User Engagement with Localized Spanish AI Models Across Hispanophone Countriescited by 1
- 2025Towards culturally-appropriate conversational AI for health in the majority world: An exploratory study with citizens and professionals in Latin Americacited by 1
Built on by
Citing papers per year: 2026: 1.
1 paper.