BackHallucination

Hallucination

Trustworthy LLMs: A Survey and Guideline for Evaluating Large Language Models’ Alignment

Liu et al. (2024)

Sub-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

LLMs can generate content that is nonsensical or unfaithful to the provided source content with appeared great confidence, known as hallucination(p. 10)

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

Other

Without clearly specifying the intentionality

Timing— Whether the risk is pre- or post-deployment

Pre-deployment

Occurring before the AI is deployed

Post-deployment

Occurring after the AI model has been trained and deployed

Other

Without a clearly specified time of occurrence

Supporting Evidence (1)

"There is a distinction between hallucination and misinformation. Misinformation mostly implies wrong or biased answers and can often be caused by bad inputs of information, but hallucination may consist of fabricated contents that conflict with the source content (i.e. intrinsic hallucination) or cannot be verified from the existing sources (i.e. extrinsic hallucination)."(p. 10)

Part of Reliability