paperSeptember 2026Unreviewed

PRISMA-LLM: An Empirical Reporting Framework for AI-Assisted Systematic Reviews

Miguel Zabaleta, Baihan Lin

Abstract

Large language models (LLMs) and AI-enabled software increasingly participate in systematic-review decisions, yet the information needed to audit these workflows is reported inconsistently. We analyze SciLitBench, a corpus of 888 review-automation papers with 14,726 annotations, to characterize changes in methods, review-stage use, evaluation and reported limitations. Automation has shifted toward LLM- and software-facing workflows, including stages that can alter the evidence base. Since 2023,

Cite

@misc{zabaleta2026prismallm,
  title = {{PRISMA-LLM: An Empirical Reporting Framework for AI-Assisted Systematic Reviews}},
  author = {Miguel Zabaleta and Baihan Lin},
  year = {2026},
  month = sep,
  eprint = {2609.11559},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.11559}
}