AI in Service Interactions

Study reveals that emotional support and practical assistance drive user relationships with mental health chatbots, with trust and satisfaction as outcomes rather than predictors.

Raggy enables rapid experimentation in retrieval-augmented generation pipelines through composable primitives and interactive debugging, reducing development friction.

Panel discussion on generative AI's multidimensional impact on HCI globally: education, industry dynamics, and funding across diverse regions and cultures.

Study identifies barriers to AIoT elderly care adoption in Beijing, proposing policy solutions addressing systemic fragmentation, digital literacy gaps, workforce shortages, and funding challenges.

Study examines how people with dementia and care partners want to use tracking technology, revealing needs for autonomy support, actionable insights, and relational understanding.

Physician-led evaluation of four large language model chatbots reveals unsafe medical advice rates from 5-13%, with potentially serious consequences for patient care.

Survey of 71 students reveals perceptions of generative AI as academically beneficial while raising concerns about privacy, reliability, and plagiarism, with strong commitment to integrity principles.

Study of 46 Turkish language teacher candidates reveals predominantly positive metaphorical views of AI in education, with 78% expressing optimism, but highlights need for ethics education.

Study of 124 Dutch L1 teachers' beliefs about generative AI in language education, examining acceptance levels, concerns, and opportunities for integration in writing, linguistics, and literature.

Ritchy chatbot combines RAG with human quality assurance at RWTH Aachen University IT support, achieving 76% satisfaction through weekly human review of all conversations.

Qualitative study of German consulting firms examining how Task-GenAI Fit framework balances generative AI efficiency gains against risks like hallucinations and skill loss.

Month-long in-home study examining how older adults interact with voice assistants, revealing persistent challenges despite LLM integration and proposing design considerations.

Study investigating emotion-adaptive eco-feedback in personal assistants through co-design methodology, generating eight design concepts integrating emotion AI for home energy management.

Cleo is a transparent conversational commerce chatbot that combines explicit ranking with constrained language generation to provide auditable product recommendations while preventing hallucination.

Research examining consumer adaptation to AI banking technologies through mixed methods reveals positive sentiment toward functional benefits alongside concerns about data security and trust.

Explore how LLM interfaces extend beyond conversations to integrate graphical elements. Research reveals user preferences vary by task, expertise, and context, enabling adaptive hybrid interface.

Neural transparency interface for LLM chatbot design enabling users to anticipate model behaviors through mechanistic interpretability visualization of behavioral trait vectors.

Full-stack e-commerce platform integrating generative AI for custom jewelry design, conversational intelligence with live commodity pricing, and real-time market data for heritage jewelry retailers.

Study using interpretive structural modeling to analyze critical failure factors of AI chatbots in academic research, revealing researcher knowledge deficiency as the primary constraint.

Agricultural advisory system integrating vision-language models and retrieval-augmented generation for reliable crop disease identification and knowledge-grounded farmer guidance.