TC-04 Claim and citation verification against source text (fact verification; claim checking; citation support check; quotation accuracy check)
Labels each claim as supported, refuted or not enough information against retrieved evidence, or rates whether a cited source supports its claim, and produces a label with evidence sentences.
What it does
Labels a claim as supported, refuted or not enough information against retrieved evidence, or checks that a cited source supports the claim it is attached to. Artefact: a label with evidence sentences, or a supported, minor-error or major-error rating per citation. Read the evidence sentences, and read repeated claims for a shared origin.
When to use it
Use when you need to check whether claims in a text, or the sources cited for them, are actually backed by the source text.
When it does not fit
Fits when the corpus or cited source contains the relevant sentence. Misfit: evidence spread across documents or needing inference, paywalled sources, and opinions or predictions extracted as claims. The minor-error class is subjective (kappa of 0.26 in one study).
Result format
The result is a table with one row per claim or citation, giving the claim, the source, the label (supported, refuted or not enough information, or a supported, minor-error or major-error rating) and the evidence sentences behind it. It names the repeated claims that share an origin.
Requirements on the material
| Property | Requirement type | Requirement |
|---|---|---|
| Content type | Always applies | requires=text |
| Unit of analysis | Always applies | requires=claim |
| Number of sources | Always applies | requires=two or more |
| Source dependence | Changes the order | prefers=independent |
| Appraises source credibility | Applies in some cases | no |
Not restricted on: Structure, Variable types, Time structure, How the sample was chosen, Level of detail available, Whether sources can be joined, Amount of material, Known data problems, Producer interest, Origin, Document genre, Language, Personal information, Security classification, Licence.
| Minimum material | Claims in separable form and the cited source or an evidence corpus that contains the relevant passage. |
|---|---|
| Additional sources needed | none |
| Not for (rules) | none |
| Not for (text) | Wrong choice when evidence is spread across documents or needs inference, the source is paywalled, or the claims extracted are opinions or predictions. The minor-error class is subjective (kappa of 0.26 in one study). |
Choosing and ordering
| Kind of technique | Verification technique, runs in step 6 |
|---|---|
| Phase tag | validate |
| Other phase tags | verify and prepare |
| Kind of finding | contradiction; gap |
| Question answered | what |
| Strongest statement it supports | describe |
| Needs as input |
|
| Makes as output |
|
| Must exist first | None |
| Loop target | return to gather |
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: judgement dependent.
| Stakes | Check | Person involved | Counts as a different method |
|---|---|---|---|
| exploratory | source-span citation | none | no |
| decision-informing | source-span citation | none | no |
| decision-informing | human review sample | needed; left out below high stakes | no |
| high-stakes | source-span citation | none | no |
| high-stakes | human review sample | needed | no |
| high-stakes | gold standard agreement | conditional | no |
| high-stakes | independent review | needed | no |
Failure modes and limits
| Model suitability | human judgement required |
|---|---|
| Typical model failure | Labels a claim as supported because a similar sentence exists, and counts a claim repeated across sources as independently confirmed. |
| Error sources | input data; language model; source selection; coder or rater judgement |
| Certainty limits | Certainty drops when evidence is spread across documents, needs inference or is behind a paywall, when labels are judged subjectively, and when repeated claims share one origin (inconsistency and indirectness). |
Related techniques
- should follow CK-19 Atomic claim decomposition and scoring (FActScore; atomic fact checking): atomic claim decomposition splits the text into the claims to be checked
- pairs with CK-17 Source-span and quotation check by code (quote-and-verify; extractive grounding; citation verification): a string match by code confirms that each cited passage exists
- pairs with IS-06 Source dependence and copy detection (source independence analysis): repeated claims may share one origin and so do not corroborate each other
Evidence and tag basis
Tested. A 2018 baseline pipeline reached 31.87 per cent accuracy even with correct evidence supplied, and annotators agreed at Fleiss kappa 0.6841 (not a statement about current models). A meta-analysis of 28 medical studies gave a pooled citation error rate of 25.4 per cent, with 11.9 per cent major errors. (Thorne et al., FEVER, arXiv 1803.05355; Jergas and Baethge, PeerJ 2015)
Tag basis: input profile inference; selection inference; sequencing inference; robustness inference. All tag values are inference unless a source is named.