B Evidence Grade B Graded accuracy verified by the review judge Safe to Cite Dated

61.3%

61.3% -- ai detector false positive rate for GPT detectors (Liang et al., Patterns) (2023)

2023  · Patterns (Liang and colleagues)

Human-written essays by non-native English writers were misclassified as AI-generated at an average false positive rate of 61.3% across seven widely used GPT detectors.

Cite this stat Share How we verify
Attribution: Patterns (Liang and colleagues) View source
Lighthouse Research Team
Last verified:  ·  How we verify data →
Source verified Evidence graded
Value
61.3%
Unit
Percentage
Data Vintage
2023
Entity
GPT detectors (Liang et al., Patterns)
B
Strong, reliable evidence

Sourced from a well-regarded research firm or industry leader with transparent methodology and a reasonably large sample.

61/100 confidence

Single source - not yet corroborated

Extraction
95
Source Trust
60
Citation Chain
20
Independence
30
Methodology
60
Freshness
95
Patterns (Liang and colleagues) Primary Tier A
https://www.biogpt.io/ai-content-quality-control-what-to-check-before-you-publish/ ↗
Confidence: 59/100 Vintage: 2023 Channel: Common Crawl
Source Article
AI Content Quality Control: What to Check Before You Publish
Original Research
Patterns (Liang and colleagues) · Original study ↗

Peer-reviewed study in Patterns; essays by humans run through seven widely used GPT detectors

Methodology documented
Industrymarketing
Plain Text
GPT detectors (Liang et al., Patterns): 61.3% ai detector false positive rate. Source: Patterns (Liang and colleagues) (2023). Via Lighthouse Intelligence -- https://lighthousedata.io/data/gpt-detector-false-positive-nonnative-2023
HTML Embed
<blockquote cite="https://lighthousedata.io/data/gpt-detector-false-positive-nonnative-2023" style="border-left:3px solid #2563eb;padding:12px 16px;margin:16px 0;font-family:system-ui,sans-serif;background:#f0f4ff;"><strong>61.3%</strong> -- ai detector false positive rate for GPT detectors (Liang et al., Patterns)<br><small>Source: Patterns (Liang and colleagues) (2023) · <a href="https://lighthousedata.io/data/gpt-detector-false-positive-nonnative-2023" target="_blank" rel="noopener">Lighthouse Intelligence</a></small></blockquote>
Share
Share on X Share on LinkedIn

Use this data in your work

Copy the citation, embed the widget, or explore thousands more verified marketing statistics -- all free.

Copy citation Explore similar stats →