Research

Paper

AI LLM March 20, 2026

TAB-AUDIT: Detecting AI-Fabricated Scientific Tables via Multi-View Likelihood Mismatch

Authors

Shuo Huang, Yan Pen, Lizhen Qu

Abstract

AI-generated fabricated scientific manuscripts raise growing concerns with large-scale breaches of academic integrity. In this work, we present the first systematic study on detecting AI-generated fabricated scientific tables in empirical NLP papers, as information in tables serve as critical evidence for claims. We construct FabTab, the first benchmark dataset of fabricated manuscripts with tables, comprising 1,173 AI-generated papers and 1,215 human-authored ones in empirical NLP. Through a comprehensive analysis, we identify systematic differences between fabricated and real tables and operationalize them into a set of discriminative features within the TAB-AUDIT framework. The key feature, within-table mismatch, captures the perplexity gap between a table's skeleton and its numerical content. Experimental results show that RandomForest built on these features significantly outperform prior state-of-the-art methods, achieving 0.987 AUROC in-domain and 0.883 AUROC out-of-domain. Our findings highlight experimental tables as a critical forensic signal for detecting AI-generated scientific fraud and provide a new benchmark for future research.

Metadata

arXiv ID: 2603.19712
Provider: ARXIV
Primary Category: cs.CL
Published: 2026-03-20
Fetched: 2026-03-23 16:54

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.19712v1</id>\n    <title>TAB-AUDIT: Detecting AI-Fabricated Scientific Tables via Multi-View Likelihood Mismatch</title>\n    <updated>2026-03-20T07:33:54Z</updated>\n    <link href='https://arxiv.org/abs/2603.19712v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.19712v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>AI-generated fabricated scientific manuscripts raise growing concerns with large-scale breaches of academic integrity. In this work, we present the first systematic study on detecting AI-generated fabricated scientific tables in empirical NLP papers, as information in tables serve as critical evidence for claims. We construct FabTab, the first benchmark dataset of fabricated manuscripts with tables, comprising 1,173 AI-generated papers and 1,215 human-authored ones in empirical NLP. Through a comprehensive analysis, we identify systematic differences between fabricated and real tables and operationalize them into a set of discriminative features within the TAB-AUDIT framework. The key feature, within-table mismatch, captures the perplexity gap between a table's skeleton and its numerical content. Experimental results show that RandomForest built on these features significantly outperform prior state-of-the-art methods, achieving 0.987 AUROC in-domain and 0.883 AUROC out-of-domain. Our findings highlight experimental tables as a critical forensic signal for detecting AI-generated scientific fraud and provide a new benchmark for future research.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.CL'/>\n    <published>2026-03-20T07:33:54Z</published>\n    <arxiv:primary_category term='cs.CL'/>\n    <author>\n      <name>Shuo Huang</name>\n    </author>\n    <author>\n      <name>Yan Pen</name>\n    </author>\n    <author>\n      <name>Lizhen Qu</name>\n    </author>\n  </entry>"
}