Verify Claims Against References

Systematically check whether document claims are accurately supported by their cited references.

~20 min with AI, ~2–3 hours without Expert review required; verification results must be assessed by a qualified reviewer.

Document + references → RefCheckr first pass → Manual review of flags → Spot-check unflagged → Corrected document

Best for

• Pre-checking referencing accuracy before MLR (Medical, Legal, Regulatory) review
• Reviewing documents that cite multiple references across many claims
• Catching reference drift in documents that have been through several revision rounds
• Conducting QC on a deliverable before client or internal review

Inputs

• The document to be verified, with clear claim-to-reference mapping
• Full text of all cited references (not abstracts alone — partial verification creates a false sense of security)
• Any approved messaging framework or key message platform for context on intended claims

Steps

1. Prepare the document

   Ensure every verifiable claim has a clear reference citation. Number or label claims if the document does not already do so.

2. Gather all reference materials

   Obtain the full text of every cited reference. Use high-quality, text-searchable PDFs. Scanned PDFs with OCR errors cause false flags.

3. Run automated first-pass verification

   Use RefCheckr or the prompt pattern below to compare claims against references. This catches numerical mismatches, language strength discrepancies, and missing qualifiers at scale.

4. Manually review every flagged item

   For each flag, open the cited reference and verify whether the claim is supported, partially supported, or unsupported. Do not accept or reject flags without checking the source.

5. Spot-check unflagged claims

   Automated tools do not catch everything. Manually spot-check 20–30% of unflagged claims, prioritising those with specific numerical data, comparative language, or endpoint results.

6. Correct, annotate, and re-verify

   Fix inaccurate claims, update references, and document the verification outcome. If significant changes were made, run the verification again to confirm corrections.

Output

A structured verification report covering every verifiable claim, with a clear verdict for each (SUPPORTED, PARTIALLY SUPPORTED, NOT SUPPORTED, CANNOT VERIFY). The report flags numerical discrepancies with exact values from both the document and the reference, highlights language strength mismatches, and notes missing qualifiers — formatted so a reviewer can work through it systematically.

Worked example: verifying a detail aid claim

Document claim:

“Drug Z reduced the risk of disease progression by 45% compared to standard of care (HR 0.55, p=0.002).”¹

Reference 1 (published paper) states:

In the per-protocol population, Drug Z was associated with a 38% reduction in the risk of disease progression compared to standard of care (HR 0.62, 95% CI: 0.44–0.87; p=0.006).

Verification output:

Check	Finding
Verdict	NOT SUPPORTED
Numerical mismatch	Document states HR 0.55 and 45% reduction. Reference states HR 0.62 and 38% reduction.
p-value mismatch	Document states p=0.002. Reference states p=0.006.
Missing qualifier	Reference specifies per-protocol population. Document implies ITT by omitting this qualifier.
Action required	Correct HR to 0.62, risk reduction to 38%, p-value to 0.006. Add “in the per-protocol population” qualifier. Confirm with study team whether ITT results are available.

This type of multi-error claim is common after several revision rounds — each edit drifts the numbers slightly further from the source.

Prompt pattern

You are a medical writing QC assistant. Your task is to verify the following claims against their cited references.

For each claim:
1. State the claim exactly as it appears in the document
2. Identify the cited reference
3. Find the relevant section of the reference that should support the claim
4. Assess whether the reference supports the claim: SUPPORTED / PARTIALLY SUPPORTED / NOT SUPPORTED / CANNOT VERIFY
5. If partially supported or not supported, explain the discrepancy
6. Flag any numerical mismatches (different p-values, percentages, sample sizes, etc.)
7. Flag any claims where the document uses stronger language than the reference

Document claims:
[INSERT DOCUMENT TEXT OR CLAIM LIST WITH REFERENCE NUMBERS]

Reference materials:
[INSERT REFERENCE TEXTS — one per reference, clearly labelled]

Rules:
- Compare claims strictly against the cited reference. Do not use your general knowledge to fill gaps.
- If a reference does not contain information relevant to the claim, mark it as NOT SUPPORTED by this reference.
- Note any qualifiers in the reference that are missing from the claim (e.g., subgroup, post-hoc, exploratory).

Customisation: For large documents, break claims into batches of 10–15 to keep AI output focused. For promotional materials, add a rule to flag any claim that implies superiority without a head-to-head comparison in the reference.

Why this works

AI excels at the mechanical comparison work — scanning dozens of claim-reference pairs for numerical mismatches, language strength discrepancies, and missing qualifiers far faster than manual review. The human reviewer handles what AI cannot: assessing whether a technically supported claim is used in a misleading context, judging whether partial support is sufficient, and catching important omissions from the references.

Common mistakes

Trusting unflagged claims as verified

A detail aid states “Treatment X reduced hospitalisations by 35%” citing Reference 3. The actual figure is 25%. Automated verification misses it because the reference does mention hospitalisations — just with different numbers. Always spot-check 20–30% of unflagged claims, especially those with specific numerical data.

Acting on false positives without checking

A claim is flagged as unsupported because the tool could not match paraphrased language to the reference text. The claim is actually fine. Review every flag against the source before making changes — false positives create unnecessary rework.

Poor reference PDF quality

A scanned PDF has OCR errors in a results table, and the tool reads “p=0.0O3” instead of “p=0.003” and flags a mismatch. Ensure reference PDFs are high-quality, text-searchable copies. Re-scan or obtain publisher PDFs where possible.

Context-blind verification

A claim about response rates is technically supported by the reference, but the document uses it in a comparative context the reference does not support. The tool sees support; the context is misleading. Assess each claim in the context of the full document narrative, not just as isolated pairs.

Assuming verification covers reference quality

Verification confirms that claims are supported by cited references. It does not check whether the cited reference is the best available evidence or whether newer data exists. Reference selection quality is a separate editorial and scientific judgement.

Tool stack

Tool	Role
RefCheckr	Primary tool — systematic claim-to-reference comparison

Complements: Scite.ai for citation context analysis (whether a citation supports, contrasts, or merely mentions a claim). Perplexity for quick fact-checking and finding source material to verify against. Zotero or EndNote for managing and organising the reference library. RefCheckr verifies whether claims are supported by cited evidence; Scite adds context on how that evidence treats the claim; Perplexity can help locate evidence; Zotero/EndNote store and organise it.

Frequently asked questions

Can AI automatically check whether every claim in a document is supported?

AI can flag likely mismatches at scale, which is valuable for long or multi-reference documents. It cannot confirm that a reference genuinely supports a claim — that still requires a human read of the cited passage. Treat AI verification as a triage layer, not a sign-off.

What's the difference between a reference existing and a reference supporting a claim?

A real reference can still be cited in the wrong context. The paper may discuss the same topic but report a different outcome, a different population, or contradict the claim. Verification means confirming the cited passage says this specific thing, not that the paper exists.

How do I handle a claim supported by multiple references?

Check each reference independently against the specific part of the claim it is cited for. If two references are cited together, confirm that each one supports the claim on its own, or that together they cover it without gaps. Unclear attribution is a common source of drift.

Does AI verification replace a fact-check?

No. AI verification catches a substantial share of mismatches quickly, but it does not replace the human fact-check required before sign-off. Use it to make the human review shorter and more focused, not to remove it.

Can AI detect when a reference is cited in the wrong context?

Sometimes. AI can flag when the cited passage reports a different endpoint, population, or outcome than the claim describes. Subtle context errors — a pooled analysis cited for a single-study claim, a post-hoc finding cited as primary — are harder to catch and benefit from expert review.

Review checklist

Human review checklist

• All flagged claims have been manually reviewed against the cited reference
• A sample of unflagged claims has been spot-checked for accuracy
• Numerical data (p-values, CIs, percentages, sample sizes) has been verified against source
• Claims use language consistent with the strength of evidence in the source (no overstatement)
• Qualifiers present in the source are preserved in the claims (subgroup, post-hoc, exploratory, etc.)
• Safety claims are verified with the same rigour as efficacy claims
• Any “NOT SUPPORTED” or “PARTIALLY SUPPORTED” flags have been resolved
• Changes made during verification have been documented
• The document is ready for formal review with reference accuracy confirmed

---

Next steps: After verifying references, run Check Promotional Compliance for promotional content or Check Document Consistency for long documents, then complete Final Human Review before submission.

---

Last reviewed: 15 April 2026