startthat.work home

CK-20 Sampling-consistency hallucination detection (SelfCheckGPT; self-consistency check)

Draw several stochastic responses to the same prompt and flag statements that the other samples do not support, and produce sentence-level consistency scores.

Check extracted resultsEvidence: TestedVerification technique, runs in step 6Strongest statement: describe

What it does

Draws several stochastic responses to the same prompt and flags statements that the other samples do not support. Artefact: sentence-level consistency scores. Read the lowest-scoring sentences.

When to use it

Use when no source document is available to check a model answer against and you need a screen for likely invented statements.

When it does not fit

Needs no external database. It does not check against the source document, and consistent errors pass.

Result format

The result is a table with one row per sentence of the response, giving its consistency score across the sampled responses. It lists the lowest-scoring sentences as the statements the other samples do not support.

Requirements on the material

PropertyRequirement typeRequirement
Content typeAlways appliesrequires=text
Unit of analysisAlways appliesrequires=claim
Appraises source credibilityApplies in some casesno

Not restricted on: Structure, Variable types, Time structure, How the sample was chosen, Level of detail available, Number of sources, Whether sources can be joined, Amount of material, Known data problems, Producer interest, Source dependence, Origin, Document genre, Language, Personal information, Security classification, Licence.

Minimum materialat least 5 stochastic samples per prompt
Additional sources needednone
Not for (rules)none
Not for (text)Wrong choice as the only check, because it does not compare with the source document and consistent errors pass. It screens for invention and does not show truth.

Choosing and ordering

Kind of techniqueVerification technique, runs in step 6
Phase tagvalidate
Other phase tagsnone
Kind of findingcontradiction
Question answeredwhat
Strongest statement it supportsdescribe
Needs as input
Makes as output
Must exist firstNone
Loop targetproceed with limit stated

Library checks by stakes

Each stakes level includes the checks of the level below it. Checks that need a person apply at high stakes only, so the process leaves them out at lower stakes (decision 38). Repeatability: repeatable with fixed settings.

StakesCheckPerson involvedCounts as a different method
exploratoryspot checkoptionalno
exploratoryrepeat runsnoneno
decision-informingspot checkoptionalno
decision-informingrepeat runsnoneno
decision-informinghuman review sampleneeded; left out below high stakesno
decision-informingsource-span citationnoneno
high-stakesspot checkoptionalno
high-stakesrepeat runsnoneno
high-stakeshuman review sampleneededno
high-stakessource-span citationnoneno
high-stakessecond technique with different assumptionsnoneconditional
high-stakesindependent reviewneededno

Failure modes and limits

Model suitabilitymodel plus code
Typical model failureRepeats the same error consistently, so the samples agree.
Error sourcesinput data; language model
Certainty limitsCertainty drops because the samples come from the same model and share its errors (risk of bias) and because tests covered one text type only (indirectness).

Evidence and tag basis

Tested. Tested on GPT-3 biographies with manual annotation (2023, abstract). (Manakul, Liusie and Gales 2023, arXiv 2303.08896)

Tag basis: input profile inference; selection inference; sequencing inference; robustness inference. All tag values are inference unless a source is named.