AI Design & Architecture

2 summarised stories about AI Design & Architecture, each linking back to the original source. Browse all topics →

Thursday, 16 July 2026

Introducing Human-Centeredness in AI-Assisted Lexicography

arXiv cs.AI 18 hours ago

Researchers propose a human-centered artificial intelligence framework for AI-assisted lexicography that emphasizes augmenting rather than replacing lexicographers. The framework identifies four dimensions for examining AI integration: the augmented lexicographer, sociotechnical context, bias, and tool design. The approach aims to preserve lexicographer agency and linguistic diversity while enabling beneficial AI integration into lexicographic workflows.

AI Design & Architecture AI Ethics & Bias AI & Human-Computer Interaction Natural Language Processing

Designing Safety-Constrained LLM Systems for Public Health Information Access

arXiv cs.AI 18 hours ago

Researchers developed a safety-constrained LLM system for public health information access focusing on maternal and child health resource navigation. The system achieved an average response time of 5.3 seconds and demonstrated consistent enforcement of safety constraints through domain-restricted retrieval augmented generation and strict boundary enforcement to prevent medical advice. The design patterns establish practical guidance for deploying LLM systems in healthcare contexts where information accuracy and accountability are critical requirements.

AI Design & Architecture AI & Healthcare AI Safety & Constraints Retrieval-Augmented Generation