Skip to main content
Home/Risks/Gipiškis2024/Model sensitivity to prompt formatting

Model sensitivity to prompt formatting

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.

"LLMs can be highly sensitive to variations in prompt formatting, such as changes in separators, casing, or spacing. Even minor modifications can lead to significant shifts in model performance, potentially affecting the reliability of model evaluations and comparisons. This sensitivity persists across different model sizes and few-shot examples [177]."(p. 28)

Other risks from Gipiškis2024 (144)