TaMPERing 大型语言模型:在公共行政研究中使用生成式 AI 的实地指南
TaMPERing with Large Language Models: A Field Guide for using Generative AI in Public Administration Research
AI总结:
本文提出 TaMPER 框架,围绕任务、模型、提示、评估和报告五个关键决策点,为公共行政研究提供使用大型语言模型的结构化方法,以解决透明度、可复现性及模型变异性等挑战。
摘要:
将大型语言模型(LLMs)整合到社会科学研究中,为推进科学探索提供了变革性机遇,特别是在公共行政(PA)领域。然而,缺乏使用 LLMs 的标准化方法,对确保透明度、可复现性和可复制性构成了重大挑战。本手稿介绍了 TaMPER 框架——一种围绕五个关键决策点构建的结构化方法:任务、模型、提示、评估和报告。TaMPER 框架为学者提供了系统的方法,以有效利用 LLMs,同时应对模型变异性、提示设计、评估协议和透明报告实践等关键挑战。
英文摘要:
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.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。