PREPRINT

TaMPERING with Large Language Models: A Field Guide for Generative AI in Public Administration Research Item Info

The PDF is not rendering in your browser, please use the button below to download the PDF.

Title:
TaMPERING with Large Language Models: A Field Guide for Generative AI in Public Administration Research
Authors:
Overton, Michael Robison, Barrie Sheneman, Luke
Year:
2025
Output Type:
Preprint
Venue:
arXiv
Venue Type:
Preprint
Status:
Under review
Theme:
Data Science and AI
Sub-theme:
AI
Abstract:
The integration of Large Language Models (LLMs) into social science research presents transformative opportunities for advancing scientific inquiry, particularly in public administration (PA). However, the absence of standardized methodologies for using LLMs poses significant challenges for ensuring transparency, reproducibility, and replicability. This manuscript introduces the TaMPER framework-a structured methodology organized around five critical decision points: Task, Model, Prompt, Evaluation, and Reporting. The TaMPER framework provides scholars with a systematic approach to leveraging LLMs effectively while addressing key challenges such as model variability, prompt design, evaluation protocols, and transparent reporting practices.
Topics:
Generative AI LLMs Research methods Reporting standards
DOI:
https://doi.org/10.48550/arXiv.2504.01037
arXiv ID:
2504.01037
Open Access Copy:
https://doi.org/10.48550/arxiv.2504.01037
OpenAlex ID:
W6929243912
Full Citation:
Overton, Michael, Barrie Robison, and Luke Sheneman. "TaMPERING with Large Language Models: A Field Guide for Generative AI in Public Administration Research." arXiv preprint arXiv:2504.01037. https://doi.org/10.48550/arXiv.2504.01037 (Under Review)
Cite this work Under review

Reference

Overton, Michael; Robison, Barrie; Sheneman, Luke (2025). TaMPERING with Large Language Models: A Field Guide for Generative AI in Public Administration Research. arXiv. [Under review].

View DOI record arXiv preprint

@misc{overton2025_tampering_with_large_lan,
  title   = {TaMPERING with Large Language Models: A Field Guide for Generative AI in Public Administration Research},
  author  = { Overton, Michael and Robison, Barrie and Sheneman, Luke },
  year    = {2025},
  howpublished = {arXiv},
  doi     = {10.48550/arXiv.2504.01037},
  eprint  = {2504.01037},
  archivePrefix = {arXiv},
  url     = {https://www.michaeloverton.net/research/items/tampering_with_large_language_models_a_field_guide_for_gener.html}
}