Magic Words or Methodical Work? Challenging Conventional Wisdom in LLM-Based Political Text Annotation

ArXi:2603.26898v1 Announce Type: cross Political scientists are rapidly adopting large language models (LLMs) for text annotation, yet the sensitivity of annotation results to implementation choices remains poorly understood. Most evaluations test a single model or configuration; how model choice, model size, learning approach, and prompt style interact, and whether popular "best practices" survive controlled comparison, are largely unexplored.