Topic 6 of 20 · Part II : Grounding, Evaluation and Orchestration

Hallucination control

Hallucination control is the disciplined management of what the model is allowed to claim : and requiring any citation is not enough.

The control pattern

Data asset

Grounding evidence and claim verification

Knobs

Source quality, Required citations, Retrieval threshold, Claim materiality, Abstention policy, Verifier strictness

Outcome

Fewer unsupported or misleading claims

Measurement

See how to measure this below

What it is

Hallucination control is the disciplined management of what the model is allowed to claim. The evidence is the data asset; source authority, citation rules, retrieval thresholds and abstention behaviour are its knobs.

It helps to distinguish several failure types, because each needs a different control: an invented fact, a real fact attached to the wrong period, a correct number with the wrong units, an interpretation presented as certainty, and a statement based on stale data. Requiring any citation is not enough if the citation does not actually support the claim.

The goal is not a timid assistant. It is one whose confidence reflects its evidence : able to say what is known, what is inferred, and what remains uncertain.

The knobs in detail

Each row is one adjustable property of the data asset, and what moving it tends to do.

KnobWhat you adjustLikely effect
Source qualityWhich sources may support which claimsStops a news recap outranking a filing
Required citationsWhat level of claim needs supportMakes verification possible at all
Retrieval thresholdMinimum evidence before answeringConverts weak grounding into abstention
Claim materialityWhich claims get the strictest checksFocuses effort on numbers and time-sensitive facts
Abstention policyWhat the system does with no supportPrevents gap-filling from memory
Verifier strictnessHow hard entailment is enforcedTrades false refusals against false claims

Applied: Stocks Assistant

In Stocks Assistant, numeric and time-sensitive statements should pass through a claim-evidence check. A statement such as “revenue grew 12%” should be decomposed into company, metric, value, comparison period, units and source. If these elements cannot be aligned to evidence, the result is qualified or withheld. Generated summaries should clearly label facts, model interpretation and market-derived signals. A confidence threshold can decide whether a small model answers, a larger teacher rechecks the evidence, or the interface asks the user to narrow the question.

How to measure it

Evidence that the knob produced the intended behaviour, rather than shifting the problem elsewhere.

  • Unsupported-claim rate at the claim level, not per answer
  • Numeric contradiction rate and wrong-period rate
  • Citation entailment : does the source actually support the claim?
  • Freshness violations
  • Appropriate abstention rate

Common mistakes

Grading a whole answer pass or fail. One bad claim in six is invisible at that resolution.

Treating a present citation as a verified citation.