Article

LLM-assisted screening and extraction for systematic reviews: workload reduction and refusal-driven missingness in a land-use evidence synthesis

2026-05-04

Abstract excerpt

<title>Abstract</title> <p>Generative AI may reduce the cost of systematic reviews, but deployed models can fail in ways that affect which evidence is included in a review. We evaluated a hosted large language model (LLM), Qwen Max, as an assistant for an environmental evidence synthesis on national-scale land-use/land-cover prediction. After retrieving 11,817 Web of Science records and screening 11,688 unique re...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 3c3c7338-860d-5030-9ea7-672c1c592cc2
DOI: 10.21203/rs.3.rs-9582053/v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

LLM-assisted screening and extraction for systematic reviews: workload reduction and refusal-driven missingness in a land-use evidence synthesisDOI 10.21203/rs.3.rs-9582053/v1Read

Operationalising LLM-assisted screening of literature to support systematic reviewsSemantic proximity Read

Careful design of Large Language Model pipelines enables expert-level retrieval of evidence-based information from conservation synthesesSemantic proximity Read

Assessing the feasibility and acceptability of a bespoke large language model pipeline to extract data from different study designs for public health evidence reviewsSemantic proximity Read

Will generative AI help solve systematic literature reviews? Evidence from a 2-year research programmeSemantic proximity Read

From Literature to Practice: Application of Large Language Models for Farm Management InsightSemantic proximity Read

Performance of Google NotebookLM for AI-assisted data extraction and consensus statement generation in a heterogenous systematic review on inflammatory bowel disease, obesity, and cardiometabolic comorbidities: A Methodological ReportSemantic proximity Read

Can Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) Generate New Knowledge for Urban Studies?Semantic proximity Read

An AI system to help scientists write expert-level empirical softwareSemantic proximity Read

Large Language Model-Assisted Data Extraction in Systematic Reviews: A Case Study of Automated Comparative Performance EvaluationSemantic proximity Read

Fully Automated Systematic Review Generation via Large Language Models: Quality Assessment and Implications for Scientific PublishingSemantic proximity Read

How good are large language models for automated data extraction from randomized trials?Semantic proximity Read

Sensitivity, specificity and avoidable workload of using a large language models for title and abstract screening in systematic reviews and meta-analysesSemantic proximity Read