Large language models for automated PRISMA 2020 adherence checking

TL;DR

This study develops a benchmark and evaluates large language models for automated adherence checking to PRISMA 2020 guidelines, demonstrating significant accuracy improvements with structured input formats.

Contribution

Introduces a shareable benchmark dataset and systematically evaluates LLMs, showing structured checklists greatly enhance adherence detection accuracy.

Findings

Structured checklists improve accuracy to ~79%.

Qwen3-Max achieves 95.1% sensitivity.

Accuracy ranges from 70.6% to 82.8% across models.

Abstract

Evaluating adherence to PRISMA 2020 guideline remains a burden in the peer review process. To address the lack of shareable benchmarks, we constructed a copyright-aware benchmark of 108 Creative Commons-licensed systematic reviews and evaluated ten large language models (LLMs) across five input formats. In a development cohort, supplying structured PRISMA 2020 checklists (Markdown, JSON, XML, or plain text) yielded 78.7-79.7% accuracy versus 45.21% for manuscript-only input (p less than 0.0001), with no differences between structured formats (p>0.9). Across models, accuracy ranged from 70.6-82.8% with distinct sensitivity-specificity trade-offs, replicated in an independent validation cohort. We then selected Qwen3-Max (a high-sensitivity open-weight model) and extended evaluation to the full dataset (n=120), achieving 95.1% sensitivity and 49.3% specificity. Structured checklist provision substantially improves LLM-based PRISMA assessment, though human expert verification remains essential before editorial decisions.