Researchers tracked first-year algebra pupils using large language models for homework
Researchers at a university tracked 23 first-year linear algebra pupils through three homework assignments of different designs that they completed using large language models.
They examined 429 prompts and compared 59 chatlogs with submitted solutions.
The prompts fell into five patterns, using the language model chiefly as a solver, explainer, or validator.
The distribution of patterns varied across assignments and ten of the 15 pupils who finished all three tasks shifted their primary pattern.
Sources behind this report
Report history
No earlier revision dates are retained here. This does not establish that the report has never changed; read any dated updates and corrections.
This brief was made by AI and checked against its cited public sources. How the newsroom works