Barbara Plank
Titles as the sources gave them. In 1 entry, with 0 checked quotations.
In the Base
Every entry they appear in.
High Scores, Hidden Failures: Evaluating Codebook-Based LLM Content Analysis
According to the abstract, Senger, Campbell, van der Goot and Plank test LLM coding pipelines for social-science text annotation across four datasets and five models. They report instability, domain sensitivity and label-level disparities hidden by accuracy and micro-F1, which persist under common optimization.