Intrinsic hallucination
An intrinsic hallucination is generated content that contradicts or is factually inconsistent with the supplied source or context.
Introduction to Generative AI, Second Edition
An intrinsic hallucination is a model-generated response that is inconsistent with information in its source material.
- How it is used
- Distinguishes contradictions of source material from claims that the source cannot confirm.
- How deep it goes
- Defines intrinsic hallucination through a hypothetical conflicting date and briefly discusses hallucination as guessing under limited or conflicting information.
- Examples
- Uses a hypothetical source date of 2006 and model response of 2016 to illustrate a contradiction.
- What you can do after
- Evaluate a response against its source material to recognize a contradiction.
Read how Introduction to Generative AI, Second Edition explains intrinsic hallucination →
LLM Evaluation and Alignment, The Foundational Ideas
An intrinsic hallucination is an output that is grounded in the provided source but factually misaligned with it.
- How it is used
- Diagnoses factual failures in closed-domain generation and retrieval-augmented generation when outputs must adhere to provided evidence.
- How deep it goes
- Defines the grounded-but-misaligned category, contrasts neighboring quadrants, and demonstrates claim-level contradiction checking.
- Examples
- Uses a financial revenue statement whose 15% growth rate is incorrectly changed to 5%.
- What you can do after
- Diagnose grounded factual errors by comparing generated claims against source claims and interpreting low-faithfulness RAGAS results.
Read how LLM Evaluation and Alignment, The Foundational Ideas explains intrinsic hallucination →
What to know first
- language modelA language model is a computational model that represents patterns in linguistic sequences to assign probabilities, predict, generate, or evaluate language.
Related concepts
- hallucinationkind of · A hallucination is model-generated content that is false, fabricated, or unsupported by relevant evidence but presented as plausible or factual.
- extrinsic hallucinationcontrasts with · An extrinsic hallucination is generated content that is unsupported by, or not inferable from, the supplied source or context.
Questions about intrinsic hallucination
What is intrinsic hallucination?
An intrinsic hallucination is generated content that contradicts or is factually inconsistent with the supplied source or context.
Which Manning books explain intrinsic hallucination?
Introduction to Generative AI, Second Edition and LLM Evaluation and Alignment, The Foundational Ideas.
What should I know before learning intrinsic hallucination?
Manning books that teach intrinsic hallucination usually introduce language model first.
What is the difference between intrinsic hallucination and extrinsic hallucination?
An intrinsic hallucination is generated content that contradicts or is factually inconsistent with the supplied source or context. An extrinsic hallucination is generated content that is unsupported by, or not inferable from, the supplied source or context.
What is intrinsic hallucination a kind of?
Intrinsic hallucination is a kind of hallucination. A hallucination is model-generated content that is false, fabricated, or unsupported by relevant evidence but presented as plausible or factual.
These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.

