PaperNPJ Science of LearningOct 3, 2024
Evaluating large language models in analysing classroom dialogue
Yun Long, Haifeng Luo, Yu Zhang
Read the original →What follows is our summary, written for district staff. It is not the paper. If this is going to inform a decision, read the original.
Evaluating large language models in analysing classroom dialogue
Article Summary
This study compared the outputs of an LLM with humans when analyzing classroom dialogue. Overall, the LLM and humans largely agreed on their coding and qualitative analysis.
Related across the site
ResearchThe GPT Surprise: Offering Large Language Model Chat in a Massive Coding Class Reduced Engagement but Increased Adopters Exam PerformancesStudents taking an online coding class were randomly assigned to a group with access to an LLM or a control condition.ResearchThe Widespread Adoption of Large Language Model-Assisted Writing Across SocietyThis paper analyzes the rate of adoption for LLMs in professional writing, specifically: job postings, press releases…