0 / 0
Downstream retraining risk for AI

Downstream retraining risk for AI

Risks associated with input
Training and tuning phase
Value alignment
New

Description

Using data from user-generated content or AI-generated content from downstream applications for retraining a model can result in misalignment, undesirable output, and inaccurate or inappropriate model behavior.

Why is downstream retraining a concern for foundation models?

Repurposing downstream output for re-training a model without implementing proper human vetting increases the chances of undesirable outputs being incorporated into the training or tuning data of the model, resulting in an echo chamber effect. Improper model behavior can result in business entities facing legal consequences or reputational harms.

Background image for risks associated with input
Example

Model collapse due to training using AI-generated content

As stated in the source article, a group of researchers from the UK and Canada have investigated the problem of using AI-generated content for training instead of human-generated content. They found that using model-generated content in training causes irreversible defects in the resulting models and that learning from data produced by other models causes model collapse.

Parent topic: AI risk atlas

Generative AI search and answer
These answers are generated by a large language model in watsonx.ai based on content from the product documentation. Learn more