Skip to main content
Home/Risks/Gipiškis2024/Models distracted by irrelevant context

Models distracted by irrelevant context

Sub-category
Risk Domain

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.

"Models can easily become distracted by irrelevant provided information (such as “context” in LLMs), leading to a significant decrease in their performance after introducing irrelevant information. This can happen with different prompting techniques, including chain-of-thought prompting [184]."(p. 28)

Other risks from Gipiškis2024 (144)