Dataset for 'A Hybrid GUI-LLM Interface Paradigm for 3D Scene Customisation'

This dataset and fine-tuning entries accompany the research paper "A Hybrid GUI-LLM Interface Paradigm for3D Scene Customisation". The research paper looks for empirical evidence of GUI-LLM modality trade-offs in 3D scene interaction. It compiles insights from testing with 12 participants who used a GUI and LLM interface to customise a 3D scene showing a digital replica of a city. The included files are: Anonymised participant task completion data: This file includes the time it took each participant to complete 12 tasks, using different interface types. Each participant completed tasks in a different order and with different interfaces. Time is recorded in seconds. Additionally, we tracked the number and type of "errors" made by each participant, as well as the times the LLM made a mistake and the participant spotted it. Fine-tune samples: 150 ad-hoc prompts and responses to fine-tune Mistral Small 3.2. This uses the traditional paradigm "system, user, assistant". System instructions: These instructions are added to the LLM to improve responses. Study tasks and follow up questions: Tasks that the participants had to perform. To protect the participants’ privacy, all data have been anonymised. Personally identifiable information and sensitive content have been removed or redacted prior to publication. The dataset is provided to support transparency and reproducibility of the research reported in the corresponding publication.