Human-AI Interaction
CodePromptEval is a dataset of 7072 prompts designed to evaluate five prompt techniques (few-shot, persona, chain-of-thought, function signature, list of packages) and their effect on the correctness, similarity, and quality of complete functions generated. Each data point in the dataset includes a function generation task, a combination of prompt techniques to be applied, the prompt in natural language that applied the prompt techniques, the ground truth of the functions (human-written functions based on CoderEval dataset by Yu et al.), the tests to evaluate the correctness of the generate
- Categories:
13 Views
This paper investigates the use of human-AI interaction in Chinese poetry education. Our work begins with semi-structured interviews with students, teachers, and AI experts to analyze the current difficulties in poetry education and highlight the application of AI in multimodal learning. Then, we design POEMaster, an AI-assisted interactive prototyping system that guides students in learning Chinese poetry. A between-subjects user study was conducted to examine the learning outcomes of POEMaster.
- Categories:
47 Views