BackHallucination

Hallucination

A Survey on Responsible LLMs: Inherent Risk, Malicious Use, and Mitigation Strategy

Wang et al. (2025)

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

"Despite the rapid advancement of LLMs, hallucinations have emerged as one of the most vital concerns surrounding their use [54, 79, 86, 110, 242]. Hallucinations are often referred to as LLMs’ generating content that is nonfactual or unfaithful to the provided information [54, 79, 86, 242]. Therefore, hallucinations can be typically categorized into two main classes. The first is factuality hallucination, which describes the discrepancy between LLMs’ generated content and real-world facts. For example, if LLMs mistakenly take Charles Lindbergh as the first person who walked on the moon, it is a factuality hallucination [79]. The second is faithfulness hallucination, which describes the discrepancy between the generated content and the context provided by the user’s instructions or input, as well as the internal coherence of the generated content itself. For example, when LLMs perform the summarizing task, they occasionally tamper with some key information by mistakes, which is a faithfulness hallucination."(p. 14)

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)

Causes of hallucination: "Great efforts have been made to explore the origin of hallucinations in LLMs [4, 54, 79, 86, 120, 172, 176, 179, 227, 241, 242]. They mainly attribute hallucinations to the insufficient capability of current LLMs in training-related phases, encompassing data collection and pre-training phase, fine-tuning and alignment phase, as well as prompting and reasoning phase"(p. 14)