Skip to content

Active/passive local/global coding framework for LLM offloading prompts

Research Method · All research methods
Evidence · 1 claim (1 for) · 1 study (1 associational), q2 · 0 of 1 report an effect size · 1 claim rests on one study

Description

A four-way coding scheme applied to each of 564 learner prompts, capturing whether the learner "remained somewhat active or was passive during a comprehension activity, and if the comprehension within a prompt was targetting local or global level". Active prompts specify learner direction (clarifying gaps, seeking evaluation or structure); passive prompts leave the LLM to act without learner-specified constraints; local refers to micro-level items and global to whole-text or cross-text structure. Reproducibility was checked against three LLM-based labelling agents, reaching an average kappa of 0.64 (passive/global) and 0.61 (local/global).

Accounts

  • Coding framework for the content of LLM offloading prompts (active/passive by local/global comprehension): A four-way coding scheme applied to each of 564 learner prompts, capturing whether the learner "remained somewhat active or was passive during a comprehension activity, and if the comprehension within a prompt was targetting local or global level". Active prompts specify learner direction (clarifying gaps, seeking evaluation or structure); passive prompts leave the LLM to act without learner-specified constraints; local refers to micro-level items and global to whole-text or cross-text structure. Reproducibility was checked against three LLM-based labelling agents, reaching an average kappa of 0.64 (passive/global) and 0.61 (local/global). (Poquet et al. (2026))

Claims

-

Key Sources

  • Poquet, O., Nanduri, M. S., Salinas Loyer, M. X., Stadler, M., Sailer, M., Jovanovic, J. (2026). Profiling Cognitive Offloading in LLM-mediated Synthesis Writing: Volume vs. Content. https://arxiv.org/abs/2606.10434. doi:10.48550/arxiv.2606.10434
Page metadata
Field Value
type research-method
id activepassive-localglobal-coding-framework-for-llm-offloading-prompts
title Active/passive local/global coding framework for LLM offloading prompts
description A four-way coding scheme applied to each of 564 learner prompts, capturing whether the learner "remained somewhat active or was passive during a comprehension activity, and if the comprehension within a prompt was targetting local or global level".
status review
generated by process:settle-candidates on 2026-10-10
trust unverified — no one has confirmed this page's content

Frontmatter is the page's machine-readable record — see the Schema & Guide.