PRISMA-LLM: a three-layer reporting framework for LLM-assisted systematic reviews

Research Method · All research methods
Evidence · 3 claims (3 for) · 1 study (1 associational), q2 · 0 of 1 report an effect size · 3 claims rest on one study

Description

PRISMA-LLM is an evidence-informed reporting framework for LLM-assisted and AI-enabled systematic-review workflows, organized to complement PRISMA 2020. It has three layers: "a universal checklist specifies the information that should be reported across LLM-assisted review workflows"; five implementation-disclosure levels organize technical detail needed to reconstruct workflows; and consequence-sensitive evaluation expectations determine when validation should exceed the minimum associated with a disclosure level. Its empirical basis is the recurring evaluation and limitation dimensions observed in SciLitBench and the association between workflow type and reporting coverage.

Accounts

• PRISMA-LLM: a three-layer reporting framework for LLM-assisted systematic reviews: PRISMA-LLM is an evidence-informed reporting framework for LLM-assisted and AI-enabled systematic-review workflows, organized to complement PRISMA 2020. It has three layers: "a universal checklist specifies the information that should be reported across LLM-assisted review workflows"; five implementation-disclosure levels organize technical detail needed to reconstruct workflows; and consequence-sensitive evaluation expectations determine when validation should exceed the minimum associated with a disclosure level. Its empirical basis is the recurring evaluation and limitation dimensions observed in SciLitBench and the association between workflow type and reporting coverage. (Zabaleta et al. (2026))

Claims

• Since 2023, software/product papers report markedly less evaluation detail than LLM papers in review automation [+M]
• Reported limitation profiles differ by automation method, with prompt sensitivity especially frequent in LLM papers [+W]
• The software-product reporting gap persists within each review stage, and reported precision and recall vary widely across approaches [+W]

Related Research Methods

-

Key Sources

• Zabaleta, M. & Lin, B. (2026). PRISMA-LLM: An Empirical Reporting Framework for AI-Assisted Systematic Reviews. https://arxiv.org/abs/2609.11559. doi:10.48550/arxiv.2609.11559

Page metadata

Field	Value
type	research-method
id	prisma-llm-a-three-layer-reporting-framework-for-llm-assisted-systematic-reviews
title	PRISMA-LLM: a three-layer reporting framework for LLM-assisted systematic reviews
description	PRISMA-LLM is an evidence-informed reporting framework for LLM-assisted and AI-enabled systematic-review workflows, organized to complement PRISMA 2020.
status	review
generated	by process:settle-candidates on 2026-10-11
trust	unverified — no one has confirmed this page's content

Frontmatter is the page's machine-readable record — see the Schema & Guide.