SOURCE-LINKED INTELLIGENCE

When Auditors Fabricate: Batch-Size Degradation and Confident Hallucination in LLM Detection of Planted Document Contamination

arXiv · AI, language, vision and robotics · article · Sep 9, 2026 · UTC

Large language models are increasingly proposed as automated auditors of document quality, yet their reliability as detectors of planted errors is poorly characterised. We construct a contaminated corpus of 150 academic papers spanning supply chain management and medical research, injecting 450 known contaminants of three types: typographical corruption, semantic reversal, and absurd out-of-context insertion. We then evaluate Google Gemini 3.0 Pro's ability to recover a 180-contaminant answer-key subset across 60 documents under three prompting regimes of increasing scale: single document, sma

Read original source ↗ Open in workspace

recordType

paper

region

Global