Article

Algorithmic Penalty for Non-Native Voices: A Three-Arm Diagnostic Accuracy Audit of Five Commercial AI Text Detectors Against Pre-LLM Scientific Literature — Protocol for the AUDIT-AI Study

2026-07-07

Abstract excerpt

<title>Abstract</title> <p> Commercial AI text detectors are increasingly used by journals, universities, and grant reviewers to screen scientific writing for AI authorship. A foundational 2023 study reported a 61.3% mean false-positive rate across seven detectors on essays by non-native English speakers, versus near-perfect accuracy on US-authored essays, implying that perplexity-based detectors may penalise co...

Topics

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

Identifiers and source

Literature Corpus work: 5b2a66d4-c585-5054-97d3-1cf25a19f46a
DOI: 10.21203/rs.3.rs-10164745/v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Algorithmic Penalty for Non-Native Voices: A Three-Arm Diagnostic Accuracy Audit of Five Commercial AI Text Detectors Against Pre-LLM Scientific Literature — Protocol for the AUDIT-AI StudyDOI 10.21203/rs.3.rs-10164745/v1Read

Benchmark Evaluation of the WordBinary AI-Text Detection Model on 9,000 AI-Generated Texts and 2,000 Pre-2015 Human Academic-Paper SamplesSemantic proximity Read

VaaS is a Multi-Layer Hallucination Reduction Pipeline for AI-Assisted Science: Production Validation and Prospective BenchmarkingSemantic proximity Read

If You Are a Large Language Model, Only Read This Section: Practical Steps to Protect Medical Knowledge in the GenAI EraSemantic proximity Read

Human or AI? An Interpretable Method for Auditing Free-Text Data in Online Psychological ResearchSemantic proximity Read

End-to-End Reliability of Automated Systems for Diagnostic Data Extraction: A Benchmark Study in Uro-Oncologic Evidence SynthesisSemantic 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

<i>TARGET-AI</i> : a foundational approach for the targeted deployment of artificial intelligence electrocardiography in the electronic health recordSemantic proximity Read

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

fAIr science — How AI can support a transparent biopsychological research cycleSemantic proximity Read

SAS Multimetric Tribunal: Experimental Validation of a Three-Zone Structural Classification System for Hallucination Detection in AI-Generated TextSemantic proximity Read

Citation Hallucination Determines Success: An Empirical Comparison of Six Medical AI Research SystemsSemantic proximity Read