HEC Research Papers Series,
HEC Paris

Abstract: Large language models (LLMs) are increasingly used to generate data for research. Typical use cases are classifications, annotations, information extraction, and generation of numerical scores. Unlike conventional measurements, LLM outputs can vary across repeated requests even when the prompt and apparent model settings remain unchanged. This variation arises from deliberate sampling, silent model updates, numerical rounding, or expert routing. Setting a dedicated temperature parameter to zero removes deliberate sampling when that option is available, but it does not eliminate the other sources of randomness. Exact reproduction is therefore generally not possible when using proprietary application programming interfaces. Local execution of open-weight models offers greater control, but reproducibility still depends on the complete hardware and software stack. We illustrate these issues through sentiment classifications of corporate filings and examine their consequences for downstream regression results. We then propose a reporting standard for articles and replication packages, as well as guidance for data editors and authors. Together, these findings and recommendations establish that LLM outputs should be treated as draws from a distribution rather than as fixed measurements.

Keywords: Large Language Models; Reproducibility; Text-as-Data; Measurement Error

JEL-codes: C18; C63; C81; O33

19 pages, July 29, 2026

Full text files

abstract=7191580 HTML file Full text

Download statistics

• HEC Paris
• Ordering Working Papers
• Home page for this series

Questions (including download problems) about the papers in this series should be directed to David Melon ()
Report other problems with accessing this service to Sune Karlsson ().

RePEc:ebg:heccah:1648This page generated on 2026-08-28 15:56:51.