Skip to main content
Home/Risks/Deng et al. (2023)/Misleading Information

Misleading Information

Towards Safer Generative Language Models: A Survey on Safety Risks, Evaluations, and Improvements

Deng et al. (2023)

Category
Risk Domain

AI systems that inadvertently generate or spread incorrect or deceptive information, which can lead to inaccurate beliefs in users and undermine their autonomy. Humans that make decisions based on false beliefs can experience physical, emotional or material harms

Large models are usually susceptible to hallucination problems, sometimes yielding nonsensical or unfaithful data that results in misleading outputs.(p. 3)

Other risks from Deng et al. (2023) (6)