HUMAN-COMPUTER INTERACTION (HCI) AND USER EXPERIENCE (UX) OF PROMPTING

Human Computer Interaction and User Experience are really important when we design applications for Large Language Models. People are starting to use prompts to talk to these machines but it is not always easy for everyone to do this. Some people know what they want but have a time telling the Large Language Model what that is. This paper is about a way to help people make prompts. It is called a Human Computer Interaction based prompting framework. This framework gives people help with making prompts suggests context checks if the prompt is good makes it better looks at the response and then refines it. The goal is to make it easier for people to make prompts and get responses from the Large Language Model. To see if this works, we tried it out. Looked at how well people could finish tasks how relevant the responses were, how long it took how many times they had to fix their prompts and if people thought it was easy to use and were happy with it. We think that prompting is not a technical problem but also a Human Computer Interaction and User Experience problem. A good Large Language Model system should not make people become experts, at making prompts. The system should help people say what they mean and still let them control what is happening. If we focus on the people using the system we can make Language Models that are easier to use can be used by everyone are clear and honest and actually work well.

[1]  Y. Zhang, Y. Zhang, M. Zhao, S. Feng, and Y.-M. Cheung, “How to Ask the AI: A User Perspective Survey for Large Language Model Prompting,” IEEE Transactions on Artificial Intelligence, 2026. [2]   S. Kim, J. Eun, Y. E. Park, K. Lee, G. Lee, and J. Lee, “PromptPilot: Exploring User Experience of Prompting with AI-Enhanced Initiative in LLMs,” International Journal of Human-Computer Interaction, vol. 41, no. 23, pp. 14779–14801, 2025. [3]       M. R. Morris, “Prompting Considered Harmful,” Communications of the ACM, vol. 67, no. 12, pp. 28–30, 2024. [4]  M. X. Liu, F. Liu, A. Fiannaca, T. Koo, L. Dixon, M. Terry, and C. Cai, “‘We Need Structured Output’: Towards User-Centered Constraints on Large Language Model Output,” in CHI Extended Abstracts, 2024. [5]   A. Ahmed and A. S. Imran, “The Role of Large Language Models in UI/UX Design: A Systematic Literature Review,” 2025. [6]  A. Desai, “Deciphering Human-AI Interactions: A Data-Driven Analysis of User Prompting Behaviors in Large Language Models,” 2025. [7]  S. De Paoli, “User Personas, Ideation and Large Language Models: A Post-Hoc Study,” International Journal of Human-Computer Studies, vol. 208, Art. no. 103690, 2026  [8]  J. Gao, S. A. Gebreegziabher, K. T. W. Choo, T. J.-J. Li, S. T. Perrault, and T. W. Malone, “A Taxonomy for Human-LLM Interaction Modes: An Initial Exploration,” arXiv preprint arXiv:2404.00405, 2024. [9]  J. Wang, W. Ma, P. Sun, M. Zhang, and J.-Y. Nie, “Understanding User Experience in Large Language Model Interactions,” arXiv preprint arXiv:2401.08329, 2024.  [10]  S. Thu and A. B. Kocaballi, “From Prompting to Partnering: Personalization Features for Human-LLM Interactions,” arXiv preprint arXiv:2503.00681, 2025.