Date
Publisher
arXiv
LLMs have demonstrated proficiency in contextualizing their outputs using
human input, often matching or beating human-level performance on a variety of
tasks. However, LLMs have not yet been used to characterize synergistic
learning in students' collaborative discourse. In this exploratory work, we
take a first step towards adopting a human-in-the-loop prompt engineering
approach with GPT-4-Turbo to summarize and categorize students' synergistic
learning during collaborative discourse. Our preliminary findings suggest
GPT-4-Turbo may be able to characterize students' synergistic learning in a
manner comparable to humans and that our approach warrants further
investigation.
Study at a glance
- Question: Can an AI tool guided by human input effectively summarize and categorize students' collaborative learning discussions?
- Setting and data: Student collaborative discourse (specific educational setting and sample size not stated in the abstract)
- Method: Exploratory study testing an AI model with human guidance (human-in-the-loop prompt engineering) to analyze student collaborative discourse
Why it matters
Large language models often match human performance across various tasks, but they have not yet been used to characterize synergistic learning in students' collaborative discourse.
Key findings
- Preliminary results suggest GPT-4-Turbo may characterize students' collaborative learning in a manner comparable to human evaluators.
- Paired with human guidance, the AI tool can summarize and categorize how students learn together during collaborative discussions.
- Large language models frequently match or exceed human-level performance across diverse tasks when contextualized with human input.
Summary drafted with AI from the paper’s abstract and may contain errors. See the full paper for details.
What is the application?
Who is the user?
Who age?
Why use AI?
