Large Language Models (LLMs), such as ChatGPT, exhibit advanced capabilities in generating text, images, and videos. However, their effective use remains constrained by challenges in prompt formulation, personalization, and opaque decision-making processes. To investigate these challenges and identify design opportunities, we conducted a two-phase qualitative study. In Phase 1, we performed in-depth interviews with eight everyday LLM users after they engaged in structured tasks using ChatGPT across both familiar and unfamiliar domains. Our findings revealed key user difficulties in constructing effective prompts, iteratively refining AI-generated responses, and assessing response reliability especially in domains beyond users' expertise. Informed by these insights, we designed a high-fidelity prototype incorporating Reflective Prompting, Section Regeneration, Input-Output Mapping, Confidence Indicators, and a Customization Panel. In Phase 2, user testing of the prototype indicated that these interface-level improvements may prove useful for reducing cognitive load, increasing transparency, and fostering more intuitive and collaborative human-AI interactions. Our study contributes to the growing discourse on human-centred AI, advocating for human-LLM interactions that enhance user agency, transparency, and co-creative interaction, ultimately supporting more intuitive, accessible, and trustworthy generative AI systems.

翻译：暂无翻译