A reporting checklist for large language models in behavioural science

2026/06/09 by Stefan Feuerriegel, Christopher Barrie, M. J. Crockett +85 · 1 voice
Medicine · Social Sciences · #Artificial Intelligence in Healthcare and Education #Computational and Text Analysis Methods #Language and cultural evolution

paper · doi:10.1038/s41562-026-02492-7

crossref issued 2026/06/09 · crossref published 2026/06/09 · crossref published-online 2026/06/09 · openalex publication_date 2026/06/09 · crossref created 2026/06/09 · openalex created_date 2026/06/10 · crossref deposited 2026/07/21 · crossref indexed 2026/07/28 · openalex updated_date 2026/07/29

Citations

• On the Dangers of Stochastic Parrots
• Leveraging AI for democratic discourse: Chat interventions can improve online political conversations at scale
• Generative Language Models Exhibit Social Identity Biases

Cited by

• A validity-guided workflow for robust large language model research in psychology

Discussions

• Our second recommendation is to use standardized reporting practices. Here is one reporting checklist that we co-authored: GUIDE-LLM. Checklists like GUIDE-LLM ensure the information needed to reprodu [bsky, 4 points, 1 comments]