TaMPERing with Large Language Models: A Field Guide for using Generative AI in Public Administration Research
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916670909448192 |
|---|---|
| author | Overton, Michael Robison, Barrie Sheneman, Lucas |
| author_facet | Overton, Michael Robison, Barrie Sheneman, Lucas |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_01037 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | TaMPERing with Large Language Models: A Field Guide for using Generative AI in Public Administration Research Overton, Michael Robison, Barrie Sheneman, Lucas Computers and Society 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. |
| title | TaMPERing with Large Language Models: A Field Guide for using Generative AI in Public Administration Research |
| topic | Computers and Society |
| url | https://arxiv.org/abs/2504.01037 |