AI-Generated-Text-Detection Tools Reported for High Error Rates

January 3, 2023

Recent reports reveal high error rates in models designed to detect text generation AI, such as AI Text Classifier and GPTZero. These tools reportedly struggle with false positives and negatives, even mistakenly flagging Shakespeare's works.

For those interested in shaping the future of safe and secure AI practices, join us at HISPI Project Cerebellum to Govern, Map, Measure, or Manage these incidents through our TAIM platform.
JOIN US

Matched TAIM controls

Suggested mapping from embedding similarity (not a formal assessment). Browse all TAIM controls

MEASURE 2.6 — similarity 0.678, rank 1. TAIM detail and related incidents →
MEASURE 2.5 — similarity 0.650, rank 2. TAIM detail and related incidents →
MAP 4.1 — similarity 0.643, rank 3. TAIM detail and related incidents →

Alleged deployer: openai, edward-tian
Alleged developer: openai, edward-tian
Alleged harmed parties: teachers, students

Source

Data from the AI Incident Database (AIID). Cite this incident: https://incidentdatabase.ai/cite/466

Data source

Incident data is from the AI Incident Database (AIID).

When citing the database as a whole, please use:

McGregor, S. (2021) Preventing Repeated Real World AI Failures by Cataloging Incidents: The AI Incident Database. In Proceedings of the Thirty-Third Annual Conference on Innovative Applications of Artificial Intelligence (IAAI-21). Virtual Conference.

Pre-print on arXiv · Database snapshots & citation guide

We use weekly snapshots of the AIID for stable reference. For the official suggested citation of a specific incident, use the “Cite this incident” link on each incident page.