Healthtech
Clinical RAG
A retrieval-augmented answering system for clinical knowledge where every answer links to its source — built so a clinician can verify the citation, not just read a plausible summary.
- pgvector
- LlamaIndex
- OpenAI
hallucinated citations in eval
source-linked answers
In short
- Every answer is composed only from retrieved passages, each linked to its approved source.
- When the corpus doesn't support a claim, the system says so instead of guessing.
- Citation support is scored on every change — an unbacked citation fails the gate before it ships.
The engagement
- Sector
- Healthcare / clinical tooling
- Company shape
- Growth-stage, regulated domain
- Engagement
- Build + eval harness
Anonymised by policy
The challenge
Clinicians won't act on a summary they can't verify. A generic chatbot that produces fluent but unsourced answers is worse than useless here — it's a liability. The system had to answer from an approved corpus and show its work for every claim.
The approach
- 1Source-linked retrieval
Every answer is assembled from retrieved passages, each rendered with a link back to the approved source document.
- 2Citation-level evaluation
The eval set scores not just answer quality but whether each cited passage actually supports the claim — hallucinated citations fail the gate.
- 3Refuse over guess
When retrieval finds no supporting source, the system says so rather than filling the gap with a plausible guess.
The solution
Queries retrieve from an approved corpus embedded in pgvector; answers are composed only from retrieved passages and rendered with inline citations. The eval harness verifies citation support on every change, and low-support answers are suppressed in favour of an explicit 'no supported answer' — so trust is earned per response.
The system we built
- Queryclinician question
- Retrieveapproved corpus, pgvector
- Compose + citeanswer from sources only
- Citation evalsupport-checked
- Answer or refuseno unsupported claims
The results
hallucinated citations in eval
on the citation eval set
source-linked answers
every shipped answer
Data & safety
- Evaluation
- A citation-support eval checks that each cited passage actually backs the claim; failures block the release.
- Guardrails
- Answers draw only from the approved corpus and refuse when retrieval finds no support.
- Data handling
- Retrieval runs over an approved corpus; no patient data is sent to third-party models.
The stack
- pgvector
- LlamaIndex
- OpenAI