Much Ado about Prompting: LLM classification of text messages from experiments

Source: Plos.org· Can Çelebi, Stefan P. Penczynski· August 4, 2026
Much Ado about Prompting: LLM classification of text messages from experiments

Researchers who classify text with large language models often possess codebooks written for human annotators. We ask how these codebooks can serve as prompts. Using three codebooks from experimental economics (one on promise classification, two on strategic …

This story was reported by Plos.org. Read the full original article:
Read on Plos.org

More in Products & Launches

View all