Auxiliary uncertainty signals for LLM-assisted systematic review screening: a benchmark across eight Cohen drug-class reviews
How hybrid BERT-LLM architectures are optimizing evidence synthesis in clinical research
Large language models (LLMs) are increasingly used for title-abstract screening in systematic reviews, but their decisions lack calibrated uncertainty. We show that an auxiliary BERT+GCN classifier supplies a structured uncertainty signal that improves LLM screening efficiency, a...
ArXiv CS.CL
Source
Generated insight by OnAirToday AI
Integrating auxiliary uncertainty signals from specialized classifiers into LLM workflows significantly boosts the precision of automated systematic review screening. This research demonstrates that targeted human-in-the-loop intervention is more efficient than letting LLMs attempt self-triage, which current models fail to perform effectively.
Comments
Keep comments relevant and respectful. No links, advertising, self-promotion, or spam.