The paper recommends prioritizing Lost Evidence and using cost-sensitive WMCC alongside MCC when assessing LLMs for literature screening in systematic reviews, supported by a review of 29 papers and large-scale reanalyses.
Wilkins, Automated title and abstract screening for scoping reviews using the gpt-4 large language model, arXiv preprint arXiv:2311.07918 (2023)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SE 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
LLM4SCREENLIT: Recommendations on Assessing the Performance of Large Language Models for Screening Literature in Systematic Reviews
The paper recommends prioritizing Lost Evidence and using cost-sensitive WMCC alongside MCC when assessing LLMs for literature screening in systematic reviews, supported by a review of 29 papers and large-scale reanalyses.