Review
Open access
Jul 2026
Qualitative Analysis of Discrepancy Patterns Between Large Language Models and Human Reviewers in Abstract Screening for Systematic Reviews.
LLM-assisted screening may improve efficiency without compromising reliability when accompanied by appropriate safeguards for ambiguous records, and many model-human disagreements reflect topic- and workflow-dependent screening conventions rather than intrinsic model failure.
K. Lee, Hakyoung Kim, Dae Sik Yang et al.
· Journal of Epidemiology · 0 citations