Zero-shot Generative Large Language Models for Systematic Review Screening Automation
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Large language models have shown promise as automated screeners, achieving competitive recall on benchmark datasets.
“Large language models (LLMs) have recently shown promise as automated screeners [Guo et al., 2024, Wang et al., 2024], achieving competitive recall on benchmark datasets.”
From Auxiliary uncertainty signals for LLM-assisted systematic review screening: a benchmark across eight Cohen drug-class reviews (2026) · cites this paper as Wang et al., 2024
The citation lists haven’t been fetched yet
References 42 · Cited by 26
- Authors
- Wang, S., Scells, H., Zhuang, S., Potthast, M., Koopman, B., & Zuccon, G.
- Affiliations
- The University of Queensland (AU)
- Leipzig University (DE)
- Commonwealth Scientific and Industrial Research Organisation (AU)
- Center for Scalable Data Analytics and Artificial Intelligence (DE)
- Corresponding author
- Wang, Shuai
- Venue
- Lecture Notes in Computer Science
- Publisher
- Springer Nature Switzerland
- Published
- 2024
- Pages
- 403-420
- ISSN
- 0302-9743 (ISSN-L)
- 1611-3349
- OpenAlex
- W4392964628
- Cited by
- 26
- References
- 42
- Citations by year
- 2026: 12 · 2025: 11 · 2024: 3
- FWCI
- 35.52
- Type
- conference paper
- Language
- en
- Open access
- closed
- Licence
- Locations
- Lecture notes in computer science (publishedVersion)
- Topics
- Social Sciences › Decision Sciences › Statistics, Probability and Uncertainty › Meta-analysis and systematic reviews
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Information Systems › Information Retrieval and Search Behavior
- Keywords
- systematic review screening, zero-shot large language models, LLM calibration, instruction tuning, ensemble learning, evidence-based medicine
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
