Answers are grounded in this paper and cite their sources.
Systematic literature reviews (SLRs) are becoming increasingly time-consuming due to the rapid growth of scientific publications.Modern artificial intelligence-based tools, especially large language models (LLM), make it possible to automate individual review stages, from screening to data synthesis.The article examines more than 20 sources and suggests a classification of such solutions according to four parameters.Comparative metrics (F1, recall) are given, and key limitations are discussed: hallucinations, reproducibility, and domain adaptation.The work is aimed at researchers who introduce AI into the practice of evidence-based analysis.
No takes yet. Share an insight, caveat, or question.
Mikriukov et al. (2025) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: