A turn-key workflow for LLM-assisted systematic-review screening.
The package ranks a corpus of titles and abstracts with an ensemble of
open-source large language models served locally by 'Ollama', then
applies the SAFE stopping rule to identify the records a human should
screen. Defaults match the four-LLM mean ensemble and the SAFE
configuration recommended by Spillias et al. (2026). A companion 'Shiny'
app walks the human reviewer through the records above the stopping
point. Complementary to the 'AIscreenR' package of
Vembye et al. (2025) <doi:10.1037/met0000769>, which targets cloud-hosted
'GPT' models via the 'OpenAI' API; 'screenllm' targets locally-served
open-weights ensembles with an integrated stopping rule.
| Version: |
0.1.0 |
| Depends: |
R (≥ 4.1.0) |
| Imports: |
cli, digest, fs, jsonlite, tibble, dplyr, rlang, httr2, glue |
| Suggests: |
shiny, bslib, DT, callr, later, writexl, readxl, testthat (≥
3.0.0), knitr, rmarkdown, readr, withr, mockery, stringdist |
| Published: |
2026-09-24 |
| DOI: |
10.32614/CRAN.package.screenllm (may not be active yet) |
| Author: |
Scott Spillias [aut, cre],
Laura Avila Turriago [aut],
Christopher Brown [aut],
Ariane Easton [aut],
Jack Roberts [aut],
Michael Sievers [aut],
Steve Swearer [aut],
Andrew Taylor [aut],
Brigette Wright [aut],
Valeriya Komyakova [aut] |
| Maintainer: |
Scott Spillias <scott.spillias at csiro.au> |
| BugReports: |
https://github.com/s-spillias/screenllm/issues |
| License: |
MIT + file LICENSE |
| URL: |
https://github.com/s-spillias/screenllm |
| NeedsCompilation: |
no |
| Citation: |
screenllm citation info |
| Materials: |
README, NEWS |
| CRAN checks: |
screenllm results |