Deriving Prompt Design Components for LLM Feedback: A Foundational Study for the PPE-LLM Framework

This supplementary document provides a detailed overview of the 55 prompt design principles developed for the PPE-LLM framework through a structured, layer-by-layer analysis. The principles were systematically derived by translating the core pedagogical and technical concepts within each layer into actionable design guidelines. They are presented across four separate tables, each corresponding to one of the framework’s layers: learner needs (Layer 1), pedagogical structure (Layer 2), best prompting practices (Layer 3), and technical considerations (Layer 4). Each table includes the principle code, a concise description, and supporting references. Explanatory notes below each table describe how the principles from that specific layer informed the development of the ten core components. This structured approach promotes transparency and traceability, allowing readers to follow how theoretical insights were methodically transformed into practical prompt design strategies. This file was independently developed by the lead author (Eyman Alyahyan) as part of her doctoral research at the School of Computing Science, University of Glasgow. It supplements the accepted publication titled "WIP: A Pedagogical Prompt Engineering Framework for LLM-Based Feedback in Higher Education (PPE-LLM)". The file was reviewed and edited from Dr. Mireilla Bikanga Ada, the academic supervisor and co-author of the main paper.

Institutions

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2025-05-26
DOI
https://doi.org/10.5281/zenodo.15520555
Primary Topic
Student Assessment and Feedback
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Deriving Prompt Design Components for LLM Feedback: A Foundational Study for the PPE-LLM Framework

Zenodo (CERN European Organization for Nuclear Research)
Student Assessment and Feedback
article

Deriving Prompt Design Components for LLM Feedback: A Foundational Study for the PPE-LLM Framework

article en

Abstract

This supplementary document provides a detailed overview of the 55 prompt design principles developed for the PPE-LLM framework through a structured, layer-by-layer analysis. The principles were systematically derived by translating the core pedagogical and technical concepts within each layer into actionable design guidelines. They are presented across four separate tables, each corresponding to one of the framework’s layers: learner needs (Layer 1), pedagogical structure (Layer 2), best prompting practices (Layer 3), and technical considerations (Layer 4). Each table includes the principle code, a concise description, and supporting references. Explanatory notes below each table describe how the principles from that specific layer informed the development of the ten core components. This structured approach promotes transparency and traceability, allowing readers to follow how theoretical insights were methodically transformed into practical prompt design strategies. This file was independently developed by the lead author (Eyman Alyahyan) as part of her doctoral research at the School of Computing Science, University of Glasgow. It supplements the accepted publication titled "WIP: A Pedagogical Prompt Engineering Framework for LLM-Based Feedback in Higher Education (PPE-LLM)". The file was reviewed and edited from Dr. Mireilla Bikanga Ada, the academic supervisor and co-author of the main paper.

Zenodo (CERN European Organization for Nuclear Research)
University of Glasgow (GB)
Quality Education
Openalex Percentile: Top 39%
Student Assessment and Feedback
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.