Anne Böckler-Raettig

Evaluating human and LLM screening workflows in a conceptually complex scoping review: Recall--workload trade-offs and run-to-run consistency

Compared human and LLM title-and-abstract screening workflows in a preregistered study embedded in a conceptually complex scoping review, finding that large language models are better suited to validated, auditable, human-supervised workflows than autonomous exclusion.