liveBook · Manning

Detection

Detection is the process of identifying whether a specified condition, abnormality, failure, or undesirable behavior is present or suspected.

How 2 Manning books explain it

LLM Evaluation and Alignment, The Foundational Ideas

Hallucination detection is the identification of generated claims or text that contain false, unsupported, or fabricated information.

How it is used
Deploys hallucination detection as a factuality dimension, production quality gate, and monitoring signal for generated responses.
How deep it goes
Decomposes detection into extraction, verification, aggregation, and action, while deferring detailed mitigation and alignment methods.
Examples
Uses customer-support policies, mixed factual claims, fabricated authorship, and fluent incorrect assistant instructions as diagnostic examples.
What you can do after
Diagnose generated responses with claim-level checks, aggregate faithfulness metrics, and production actions such as review, blocking, or regeneration.

Read how LLM Evaluation and Alignment, The Foundational Ideas explains detection →

Machine Learning Platform Engineering

Hallucination detection is the identification of generated claims that are fabricated, unsupported, or absent from trusted context.

How it is used
Deploys hallucination detection as a factuality or source-grounding validator in production LLM safety pipelines.
How deep it goes
Distinguishes rule-based, local ML, and LLM validators, but does not detail hallucination-scoring algorithms or evaluation procedures.
Examples
Uses the Guardrails AI Hub validator marketplace as the concrete implementation context.
What you can do after
Evaluate generated claims through an LLM-based validator when nuanced factuality or source-grounding judgments are required.

Read how Machine Learning Platform Engineering explains detection →

Also covered in

What to know first

Related concepts

Questions about detection

What is detection?

Detection is the process of identifying whether a specified condition, abnormality, failure, or undesirable behavior is present or suspected.

Which Manning books explain detection?

LLM Evaluation and Alignment, The Foundational Ideas and Machine Learning Platform Engineering.

What should I know before learning detection?

Manning books that teach detection usually introduce human-in-the-loop and metric first.

What is the difference between detection and anomaly detection?

Detection is the process of identifying whether a specified condition, abnormality, failure, or undesirable behavior is present or suspected. Anomaly detection is the identification of observations, events, or behaviors that substantially deviate from expected patterns or a normal baseline.

What is detection part of?

Detection is part of exception. An exception is a runtime signal or value representing an abnormal condition that interrupts ordinary program flow and can be handled or propagated.

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.