Caesar AI Atlas
Metrics • Intermediate

Citation Precision vs Citation Recall

A side-by-side comparison of Citation Precision and Citation Recall. Understand how correct support for cited claims differs from exposing the source documents used to produce a response.

Quick Verdict: Use Citation Precision to assess whether citations support attached claims; use Citation Recall to assess whether the response cites the evidence base it relied on.

At a Glance

Citation Precision

Citation Precision measures metric that measures the share of citations in a model output that correctly support the claims they are attached.

Key Characteristics
  • • Measures the share of citations that correctly support attached claims
  • • Indicates whether cited sources contain relevant evidence
  • • Supports verification of response claims
Watch Out For
  • • High precision does not mean all relevant sources were cited
  • • Needs claim-level checking rather than citation counting only

Context: Most relevant when evaluating whether model citations are accurate and useful for verification.

VS
Citation Recall

Citation Recall measures metric that measures the share of source documents used to produce a response that are actually cited in the response.

Key Characteristics
  • • Measures the share of source documents used to produce a response that are cited
  • • Indicates how much of the evidence base is exposed
  • • Supports transparency about relied-upon sources
Watch Out For
  • • High recall does not guarantee each citation supports a specific claim
  • • Can encourage over-citation if not balanced with precision

Context: Most relevant when evaluating whether a response discloses the main evidence sources behind it.

Key Differences

AspectCitation PrecisionCitation Recall
What it measuresCitation precision measures whether citations correctly support the claims they are attached to.Citation recall measures whether the source documents used to produce the response are actually cited.
Best use caseBest for checking claim support and preventing decorative or misleading citations.Best for checking evidence coverage and whether relied-upon sources are visible to the reader.
Failure modeLow precision means citations do not support the claims they appear to verify.Low recall means important source documents were used but not exposed in the response.
Threshold sensitivityPrecision can fall when extra citations are attached without claim-level relevance.Recall can rise when more sources are cited, but that may reduce readability or precision.
Common mistakeCounting citations as correct without checking the claim they support.Assuming a response is well-supported just because it cites many documents.
Caesar AI Note

In practice, citation precision protects the reader from false support, while citation recall protects the reader from hidden evidence. Strong systems need both.

Notes

Common Mistakes

1

Treating every citation as valid without checking support.

2

Optimizing for many citations instead of useful citations.

3

Ignoring uncited source documents used by the system.

4

Evaluating citations separately from the claims they verify.

When to Use Each

citation-precision

Use Citation Precision when the goal is to evaluate whether each citation actually supports the claim it is attached to. It is central for grounded answer quality, legal research, compliance summaries, and RAG evaluation.

citation-recall

Use Citation Recall when the goal is to evaluate whether the response cites the evidence base used to produce it. It is useful for transparency, auditability, and source coverage in retrieval-based systems.

Compliance Note

For AI assurance evidence, citation metrics should be tied to groundedness, traceability, and review workflows. NIST AI RMF-style evaluations should avoid relying on citation count alone and should test both support quality and source coverage.

FAQ

Can citation precision be high while citation recall is low?+

Yes. The citations that appear may be accurate, but the response may omit other source documents that were used to produce the answer.

Can citation recall be high while citation precision is low?+

Yes. The response may cite many or most source documents, but some citations may not actually support the attached claims.

Which metric matters more for legal or compliance content?+

Citation precision is critical because unsupported citations can mislead readers. Citation recall is also important where auditability and evidence coverage matter.

Recently Viewed

No recently viewed comparisons yet.