RESEARCH · RESEARCH · #1000
CRISS: Retrieval-augmented chatbot to support cancer registrars (arXiv:2609.29075v1)
Researchers introduce CRISS (Cancer Registry Intelligent Support System), a retrieval-augmented generation (RAG) conversational assistant built on a domain-specific knowledge base of national cancer registry standards to provide citation-supported guidance to cancer registrars. In evaluations using an LLM-as-a-Judge protocol across easy/medium/hard question tiers, RAG configurations outperformed non-RAG baselines (mean grounding scores 0.62/0.56/0.59 vs 0.29/0.26/0.29); proprietary RAGs led on easy/medium items while local RAGs ranked highest on hard items, and RAGs achieved higher semantic-similarity scores overall.
KEY POINTS
- Researchers introduce CRISS (Cancer Registry Intelligent Support System), a retrieval-augmented generation (RAG) conversational assistant built on a domain-specific knowledge base of national cancer registry standards to provide citation-supported guidance to cancer registrars.
- In evaluations using an LLM-as-a-Judge protocol across easy/medium/hard question tiers, RAG configurations outperformed non-RAG baselines (mean grounding scores 0.62/0.56/0.59 vs 0.29/0.26/0.29); proprietary RAGs led on easy/medium items while local RAGs ranked highest on hard items, and RAGs achieved higher semantic-similarity scores overall.
- This shows domain-specific RAG can substantially improve evidence-grounded assistance for cancer registrars, enabling citation-supported decision support while keeping human oversight.
WHY IT MATTERS
This shows domain-specific RAG can substantially improve evidence-grounded assistance for cancer registrars, enabling citation-supported decision support while keeping human oversight.