PromptRiskDBThreat intelligence atlas
AI Risk

Hallucinations

Significant concerns are raised about LLMs inadvertently generating false or misleading information, as well as erroneous code. Papers not only critically analyze various types of reasoning errors in LLMs but also examine risks associated with specific types of misinformation, such as medical hallucinations. Given the propensity of LLMs to produce flawed outputs accompanied by overconfident rationales and fabricat...

AI Risk3. Misinformation3.1 > False or misleading information2 - Post-deployment

Record summary

A quick snapshot of what this page covers.

Techniques1Attack methods connected to this risk.
Mitigations0Defenses that may help with related attacks.
Domain3. MisinformationThe broad risk area this belongs to.

Risk profile

How this risk is described and categorized.

Significant concerns are raised about LLMs inadvertently generating false or misleading information, as well as erroneous code. Papers not only critically analyze various types of reasoning errors in LLMs but also examine risks associated with specific types of misinformation, such as medical hallucinations. Given the propensity of LLMs to produce flawed outputs accompanied by overconfident rationales and fabricated references, many sources stress the necessity of manually validating and fact-checking the outputs of these models.

Domain3. Misinformation
Subdomain3.1 > False or misleading information
Entity2 - AI
Intent2 - Unintentional
Timing2 - Post-deployment
CategoryHallucinations
Subcategoryn/a

Suggested mitigations

Defenses that may help with related attacks.

No propagated mitigations. No defense is available through the connected attack methods.

Source

Research source for this risk, when available.