A bottom-up taxonomy of seven student LLM usage categories organized into three support types¶
Research Method · All research methods
Evidence · 2 claims (2 for) · 1 study (1 associational),q1· 0 of 1 report an effect size · 2 claims rest on one study
Description¶
The article presents a refined bottom-up coding scheme of students' LLM use, derived iteratively from LLM-use reports in a research-oriented course and cross-labeled by student initiative. The final scheme has seven categories (Improving Language, Confirming Ideas, Generating Ideas, Summarizing, Generating Answers, Information Extraction, Clarifying Concepts), which the article says are "organized into three higher-level types of support types based on the role the LLM played in the student's work": student-driven support, LLM-driven support, and comprehension support.
Accounts¶
- A bottom-up taxonomy of seven student LLM usage categories organized into three support types (student-driven, LLM-driven, comprehension): The article presents a refined bottom-up coding scheme of students' LLM use, derived iteratively from LLM-use reports in a research-oriented course and cross-labeled by student initiative. The final scheme has seven categories (Improving Language, Confirming Ideas, Generating Ideas, Summarizing, Generating Answers, Information Extraction, Clarifying Concepts), which the article says are "organized into three higher-level types of support types based on the role the LLM played in the student's work": student-driven support, LLM-driven support, and comprehension support. (Minju Park et al. (2026))
Claims¶
- Students whose LLM use was mostly student-driven support scored higher on Midterm 1 than LLM-driven users (about 10%), but the two groups converged on later midterms [+M]
- Individual trajectories suggest heavy LLM use focused on support other than full answer generation can coexist with improving scores, whereas reliance on LLM-generated summaries was associated with declining scores [+W]
Related Research Methods¶
Key Sources¶
- Minju Park, Ivan Orozco Vasquez, and Cristina Conati. (2026). Characterizing Students' LLM Usage Behaviors and Their Association with Learning in Critical Thinking Tasks. https://arxiv.org/abs/2605.04534
Page metadata
| Field | Value |
|---|---|
type |
research-method |
id |
a-bottom-up-taxonomy-of-seven-student-llm-usage-categories-organized-into-three-support-ty |
title |
A bottom-up taxonomy of seven student LLM usage categories organized into three support types |
description |
The article presents a refined bottom-up coding scheme of students' LLM use, derived iteratively from LLM-use reports in a research-oriented course and cross-labeled by student initiative. |
status |
review |
generated |
by process:settle-candidates on 2026-10-11 |
trust |
unverified — no one has confirmed this page's content |
Frontmatter is the page's machine-readable record — see the Schema & Guide.