Incident 106: Korean Chatbot Luda Made Offensive Remarks towards Minority Groups

Description: A Korean interactive chatbot was shown in screenshots to have used derogatory and bigoted language when asked about lesbians, Black people, and people with disabilities.

Tools

New ReportNew ReportNew ResponseNew ResponseDiscoverDiscover

Incident Stats

Incident ID
106
Report Count
13
Incident Date
2020-12-23
Editors
Sean McGregor, Khoa Lam

GMF Taxonomy Classifications

Taxonomy Details

Known AI Goal

Chatbot

Known AI Technology

Autoencoder, Distributional Learning

Known AI Technical Failure

Adversarial Data, Distributional Bias, Unauthorized Data, Inadequate Anonymization, Inappropriate Training Content, Unsafe Exposure or Access

Variants

A "variant" is an incident that shares the same causative factors, produces similar harms, and involves the same intelligent systems as a known AI incident. Rather than index variants as entirely separate incidents, we list variations of incidents under the first similar incident submitted to the database. Unlike other submission types to the incident database, variants are not required to have reporting in evidence external to the Incident Database. Learn more from the research paper.

Similar Incidents

By textual similarity

Did our AI mess up? Flag the unrelated incidents