startthat.work home

CK-16 Entailment-based consistency check (textual entailment; NLI (natural language inference) consistency; SummaC; FactCC; faithfulness checking)

Score whether each sentence of a summary or answer is supported by the source sentences, and produce a consistency score per sentence and per summary.

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

What it does

Scores whether each sentence of a summary or answer is supported by the source sentences. Artefact: a consistency score per sentence and per summary. Use it as triage, then read the unsupported sentences.

When to use it

Use when a model has summarised or answered from a document and you want to find the sentences the source does not support.

When it does not fit

Fits summarisation of a single document. Misfit: claims needing numerical reasoning or multi-document synthesis (not confirmed). Whether current LLM judges agree with human reviewers was not verified.

Result format

The result is a table with one row per sentence of the summary or answer, giving the consistency score and the supporting source sentence where one exists, plus a consistency score for the whole summary. It lists the unsupported sentences for a person to read.

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 materialthe source text and the generated text to be checked
Additional sources needednone
Not for (rules)none
Not for (text)Wrong choice for claims that need numerical reasoning or multi-document synthesis, which was not confirmed to work. Use the score as triage and read the unsupported sentences.

Choosing and ordering

Kind of techniqueVerification technique, runs in step 6
Phase tagvalidate
Other phase tagsreport
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
decision-informingspot checkoptionalno
decision-informinghuman review sampleneeded; left out below high stakesno
decision-informingsource-span citationnoneno
high-stakesspot checkoptionalno
high-stakeshuman review sampleneededno
high-stakessource-span citationnoneno
high-stakesgold standard agreementconditionalno
high-stakesindependent reviewneededno

Failure modes and limits

Model suitabilitymodel plus code
Typical model failureAccepts a plausible paraphrase that changes a number or a hedge.
Error sourcesinput data; language model
Certainty limitsCertainty drops for numeric or multi-document claims (indirectness) and when the checker model shares the generator's errors (risk of bias).

Evidence and tag basis

Tested. Entailment measures correlated better with human faithfulness ratings than standard summary metrics (2020). One entailment-based checker reached 74.4 per cent balanced accuracy on its benchmark, about 5 points above earlier work (2021), so errors remain. (Maynez et al. 2020, ACL; Laban et al. 2021, SummaC; Kryscinski et al., arXiv 1910.12840)

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