Towards culturally-appropriate conversational AI for health in the majority world: An exploratory study with citizens and professionals in Latin America

arXiv:2507.01719 · cs.HC, cs.AI · Submitted 2025-07-02 · Read on arXiv

cs.HC, cs.AI

Submitted: 2025-07-02

Updated: 2025-07-02

DOI: 10.1007/s43681-026-01196-y

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Alignment — 4× in this paper · explained in 1 episode
• Adaptation — 3× in this paper · explained in 1 episode
• Hallucination — 3× in this paper · explained in 3 episodes
• Affordance — 2× in this paper · explained in 1 episode
• Data Provenance — 2× in this paper · explained in 2 episodes
• Provenance — 2× in this paper · explained in 3 episodes
• Reinforcement Learning — 2× in this paper · explained in 4 episodes
• Taxonomy of Cultural Elements — 2× in this paper
• Actor — 1× in this paper · explained in 3 episodes
• Benchmarking — 1× in this paper · explained in 3 episodes
• Direct Preference Optimizations — 1× in this paper
• Entanglement — 1× in this paper · explained in 3 episodes
• Instruction Tuning — 1× in this paper · explained in 2 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Reinforcement Learning with Human Feedback — 1× in this paper

Sources

• PersianLLaMA: Towards Building First Persian Large Language Model
• SERENGETI: Massively Multilingual Language Models for Africa
• Towards Measuring and Modeling "Culture" in LLMs: A Survey
• Lugha-Llama: Adapting Large Language Models for African Languages
• Assessing Cross-Cultural Alignment between ChatGPT and Human Societies: An Empirical Study
• Taiwan LLM: Bridging the Linguistic Divide with a Culturally Aligned Language Model
• Culturally Aware and Adapted NLP: A Taxonomy and a Survey of the State of the Art
• Bridging the Data Provenance Gap Across Text, Speech and Video
• Survey of Cultural Awareness in Language Models: Text and Beyond
• Typhoon 2: A Family of Open Text and Multimodal Thai Large Language Models

Related papers

• Calibrating LLM Explanations to Human Decisions with Reinforcement Learning
• Rethinking Opinion Measurement Interfaces for Human-in-the-Loop Optimization
• EduGage: A Multimodal Dataset and Benchmark for Sensor-Based Momentary Assessment of Engagement in Self-Guided Video Learning
• EvoDesign: Agentic Editable Diagram Creation via Design Expertise Evolution
• HAGI++: Head-Assisted Gaze Imputation and Generation
• Explanation User Interfaces: A Systematic Literature Review