Large language models for automated PRISMA 2020 adherence checking

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Kataoka, Yuki, So, Ryuhei, Banno, Masahiro, Tsujimoto, Yasushi, Takayama, Tomohiro, Yamagishi, Yosuke, Tsuge, Takahiro, Yamamoto, Norio, Suda, Chiaki, Furukawa, Toshi A.
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909915865415680
author Kataoka, Yuki
So, Ryuhei
Banno, Masahiro
Tsujimoto, Yasushi
Takayama, Tomohiro
Yamagishi, Yosuke
Tsuge, Takahiro
Yamamoto, Norio
Suda, Chiaki
Furukawa, Toshi A.
author_facet Kataoka, Yuki
So, Ryuhei
Banno, Masahiro
Tsujimoto, Yasushi
Takayama, Tomohiro
Yamagishi, Yosuke
Tsuge, Takahiro
Yamamoto, Norio
Suda, Chiaki
Furukawa, Toshi A.
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2511_16707
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Large language models for automated PRISMA 2020 adherence checking
Kataoka, Yuki
So, Ryuhei
Banno, Masahiro
Tsujimoto, Yasushi
Takayama, Tomohiro
Yamagishi, Yosuke
Tsuge, Takahiro
Yamamoto, Norio
Suda, Chiaki
Furukawa, Toshi A.
Software Engineering
Artificial Intelligence
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.
title Large language models for automated PRISMA 2020 adherence checking
topic Software Engineering
Artificial Intelligence
url https://arxiv.org/abs/2511.16707