Article

Disagreement as a signal: an auditable dual-LLM and human-arbitrated workflow for methodological quality assessment in preclinical complex-intervention evidence

2026-07-01

Abstract excerpt

<title>Abstract</title> <p>Background: Artificial intelligence tools, especially large language models (LLMs), are increasingly entering evidence synthesis workflows. Methodological quality assessment, however, is not merely information extraction. When judgments involve non-specific factors of complex interventions, domain-specific controls, and context-dependent scoring rules, LLM outputs must be embedded withi...

Topics

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

Identifiers and source

Literature Corpus work: 0e1b0472-5871-5101-a6a1-a045f157bbc8
DOI: 10.21203/rs.3.rs-10038039/v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Disagreement as a signal: an auditable dual-LLM and human-arbitrated workflow for methodological quality assessment in preclinical complex-intervention evidenceDOI 10.21203/rs.3.rs-10038039/v1Read

The Comparability of Manual vs. Algorithm-Based Calculation of Clinical Trial Methodological Quality IndicesSemantic proximity Read

Stage-wise algorithmic bias, its reporting, and relation to classical systematic review biases in AI-based automated screening in health sciences: A structured literature reviewSemantic proximity Read

The limits of inductive reasoning for clinical evidence appraisal – a simulation study (Protocol)Semantic proximity Read

Methodological review to develop a list of bias items for adaptive clinical trials: Protocol and rationaleSemantic proximity Read

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

Artificial Intelligence in Systematic Reviews: Overcoming Reproducibility, Bias and Validation ChallengesSemantic proximity Read

Data extraction error in pharmaceutical versus non-pharmaceutical interventions for evidence synthesis: Study protocol for a crossover trialSemantic 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

Inductive reasoning with large language models: a simulated randomized controlled trial for epilepsySemantic proximity Read

ACCORD-AI: an exploratory evaluation of large language models for drafting consensus voting itemsSemantic proximity Read

GPT for RCTs?: Using AI to determine adherence to reporting guidelinesSemantic proximity Read

Can a Large Language Model Serve as the Missing Second Reviewer? Prominence Bias, Retrieval Effects, and a Confidence-Fabrication Gap in an Empirical Evaluation of Two Published Meta-AnalysesSemantic proximity Read