Groundedness / faithfulness
Share of claims supported by source (transcript, chart, cited reference); claim extraction plus entailment.
What groundedness / faithfulness means
Share of claims supported by source (transcript, chart, cited reference); claim extraction plus entailment.
Why it matters. A fluent answer can contain claims the source never supports. Groundedness checks every claim against evidence.
A note says 'denies fever' but the transcript never discusses temperature.
How to measure it
Define the unit
Decide whether you count per sentence, per note, per patient or per call.
Sample on purpose
Pick cases that cover specialties, languages and rare events, not only easy ones.
Judge with clinicians
Clinicians label a sample. Graders are then checked against those labels.
Report the margin
Show an interval, and the grader's own error rate beside the score.
A single average hides rare, serious errors and weaker subgroups.
A number with a clear unit, a stated sample, a margin and the grader's agreement with clinicians.
Report the unit (per sentence, per note, per patient), the sampling method, the severity scale, and how often the automated grader agreed with clinicians compared with how often clinicians agreed with each other.
Reviewed by the Precision research team.
How strong is the evidence
E4 · Recalled, not verified. Recalled from background knowledge and not verified. Treat it as a lead for investigation, not a finding.
What the sources say
FActScore/VeriFact-style methods are E4 in healthcare; hallucination detection AUC 0.79-0.94 in a preprint (summary).
- Automatable. Can be scored by software, including an AI grader that is spot-checked against clinicians.
- Clinician judgement. Needs a clinician to judge or label, because the answer depends on clinical meaning.
- summaryblog.pebblous.ai
Found something out of date? Write to hello@precision.example.
Agents that measure this
Quick answers
What is groundedness / faithfulness in healthcare AI?
Share of claims supported by source (transcript, chart, cited reference); claim extraction plus entailment. It sits in the every product type group.
Why does groundedness / faithfulness matter?
A fluent answer can contain claims the source never supports. Groundedness checks every claim against evidence. A note says 'denies fever' but the transcript never discusses temperature.
How is groundedness / faithfulness measured?
Define the unit, then Sample on purpose, then Judge with clinicians, then Report the margin. Report the unit (per sentence, per note, per patient), the sampling method, the severity scale, and how often the automated grader agreed with clinicians compared with how often clinicians agreed with each other.
What should I watch out for with groundedness / faithfulness?
A single average hides rare, serious errors and weaker subgroups. A good report gives: a number with a clear unit, a stated sample, a margin and the grader's agreement with clinicians.
Can groundedness / faithfulness be automated?
Only in part. It needs automatable and clinician judgement. Software can screen, but a clinician must judge the cases that matter.