BackKnowledge conflicts in retrieval-augmented LLMs

Knowledge conflicts in retrieval-augmented LLMs

Risk Sources and Risk Management Measures in Support of Standards for General-Purpose AI Systems

Gipiškis et al. (2024)

Sub-category

Risk Domain

7AI System Safety, Failures & Limitations

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.

"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]."(p. 28)

Entity: Who or what caused the harm

Human

Due to a decision or action made by humans

AI system

Due to a decision or action made by an AI system

Other

Due to some other reason or is ambiguous

Intent: Whether the harm was intentional or accidental

Intentional

Due to an expected outcome from pursuing a goal

Unintentional

Due to an unexpected outcome from pursuing a goal