← Browse all papers
Research theme
Systematic Review Automation
The Systematic Review Automation theme comprises 305 papers in this corpus published between 1974 and 2026. Work here is dominated by Design Science, Literature Review, Empirical Study. 5 open research gaps have been surfaced in this area.
Methodology profile
- Design Science79 (26%)
- Literature Review55 (18%)
- Empirical Study36 (12%)
- Experimental23 (8%)
- Conceptual22 (7%)
- Case Study18 (6%)
Research domains
- Literature Discovery207 (68%)
- Knowledge Synthesis82 (27%)
- Scholarly Infrastructure7 (2%)
- Peer Review4 (1%)
- Multi-Domain2 (1%)
- Doctoral Training1 (0%)
Frequent sub-topics
Automated research gap identification using embeddings and LLMs in systematic literature reviews · 1Multi-model embedding combinations for SLR screening · 1AI-driven research gap identification using embeddings and clustering · 1bibliometric analysis of AI in medical imaging research, generative and foundation-based methods · 1bibliometric analysis of human factors in maritime accidents · 1metadata and topic modeling analysis of circular economy literature · 1LLM-assisted data extraction and consensus statement generation · 1LLM-based PRISMA 2020 guideline adherence checking · 1
Open research gaps
- Limited COS development in neurology despite success in other fields
- The authors identify several gaps: (1) Need for validated stopping rules and acceptable performance thresholds for ML-assisted SLRs which currently are not defined; (2) Lack of prospective validation
- Need for disease-specific COS guidance for trialists
- Extension to full-text analysis beyond abstracts to capture methodological details and contextual nuances for improved classification accuracy on complex dimensions
- A stronger future study would compare the multi-stage pipeline against simpler baselines, include human ratings for output usefulness and citation quality, and measure stage-level latency and completi
Representative papers
- Artificial intelligence and the conduct of literature reviewsGerit Wagner · 2021 · 275 citations
- Artificial intelligence for literature reviews: opportunities and challengesF. J. Bolaños · 2024 · 188 citations
- The emergence of large language models as tools in literature reviews: a large language model-assisted systematic reviewDmitry Scherbakov · 2025 · 95 citations
- Large language models for conducting systematic reviews: on the rise, but not yet ready for use—a scoping reviewJudith-Lisa Lieberum · 2025 · 91 citations
- Automating Systematic Literature Reviews with Retrieval-Augmented Generation: A Comprehensive OverviewBinglan Han · 2024 · 45 citations
- A guide for structured literature reviews in business research: The state-of-the-art and how to integrate generative artificial intelligenceFabian Tingelhoff · 2024 · 35 citations
- Synthesizing scientific literature with retrieval-augmented language modelsAkari Asai · 2026 · 14 citations
- Artificial Intelligence in Literature Review Synthesis: A Step-by-Step Methodological Approach for Researchers and AcademicsMatolwandile Mzuvukile Mtotywa · 2026 · 5 citations