MIT AI Risk Repository · Risk Sub-Category · 62.19.09

Knowledge conflicts in retrieval-augmented LLMs

Category: Attacks on GPAIs/GPAI Failure Modes

Description

"AI models can be particularly sensitive to coherent external evidence, even when they come into conflict with the models’ prior knowledge. This may lead to models producing false outputs given false information during the retrieval- augmentation process, despite only a relatively small amount of false informa- tion input that is inconsistent with the model’s prior knowledge trained on much larger amounts of data [220]."

From Risk Sources and Risk Management Measures in Support of Standards for General-Purpose AI Systems (Gipiškis2024), as extracted by the MIT AI Risk Repository (CC BY 4.0).

Classification

Causal entity
AI

Subdomain definition: AI systems that fail to perform reliably or effectively under varying conditions, exposing them to errors and failures that can have significant consequences, especially in critical applications or areas that require moral reasoning.

Real-world incidents in this subdomain

Browse all incidents in this subdomain

How other frameworks describe this risk

Other entries from Gipiškis2024