Cutting Through the Clutter: The Potential of LLMs for Efficient Filtration in Systematic Literature Reviews

Simple item page
dc.contributor.authorJoos, Lucasen_US
dc.contributor.authorKeim, Daniel A.en_US
dc.contributor.authorFischer, Maximilian T.en_US
dc.contributor.editorSchulz, Hans-Jörgen_US
dc.contributor.editorVillanova, Annaen_US
dc.date.accessioned2025-05-26T06:30:59Z
dc.date.available2025-05-26T06:30:59Z
dc.date.issued2025
dc.description.abstractSystematic literature reviews (SLRs) are essential but labor-intensive due to high publication volumes and inefficient keywordbased filtering. To streamline this process, we evaluate Large Language Models (LLMs) for enhancing efficiency and accuracy in corpus filtration while minimizing manual effort. Our open-source tool LLMSurver presents a visual interface to utilize LLMs for literature filtration, evaluate the results, and refine queries in an interactive way. We assess the real-world performance of our approach in filtering over 8.3k articles during a recent survey construction, comparing results with human efforts. The findings show that recent LLM models can reduce filtering time from weeks to minutes. A consensus scheme ensures recall rates >98.8%, surpassing typical human error thresholds and improving selection accuracy. This work advances literature review methodologies and highlights the potential of responsible human-AI collaboration in academic research.en_US
dc.description.sectionheadersVisual Analytics Applications and Systems
dc.description.seriesinformationEuroVis Workshop on Visual Analytics (EuroVA)
dc.identifier.doi10.2312/eurova.20251105
dc.identifier.isbn978-3-03868-283-7
dc.identifier.issn2664-4487
dc.identifier.pages6 pages
dc.identifier.urihttps://doi.org/10.2312/eurova.20251105
dc.identifier.urihttps://diglib.eg.org/handle/10.2312/eurova20251105
dc.publisherThe Eurographics Associationen_US
dc.rightsAttribution 4.0 International License
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectCCS Concepts: Human-centered computing → Interactive systems and tools; Computing methodologies → Artificial intelligence; Applied computing → Publishing
dc.subjectHuman centered computing → Interactive systems and tools
dc.subjectComputing methodologies → Artificial intelligence
dc.subjectApplied computing → Publishing
dc.titleCutting Through the Clutter: The Potential of LLMs for Efficient Filtration in Systematic Literature Reviewsen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
eurova20251105.pdf
Size:
4.22 MB
Format:
Adobe Portable Document Format
Download
Collections
EuroVA2025