Ask NICE, get evidence: a high-precision RAG for UK guidelines

Kari Jaaskelainen

06 Oct 2025 — 1 min read

From 300 guidelines to precise answers—grounded, not guessed.

This RAG system uses a hybrid retriever over 10,195 chunks (from 300 NICE guidelines). Retrieval shines: MRR 0.814; 81% recall at first chunk and 99.1% within top 10 (7,901 queries). In generation (70 QA pairs), RAG lifted O4-Mini faithfulness by 64.7 points to 99.5%, and achieved perfect context precision (1), outperforming Meditron3-8B on faithfulness.

Why it matters: Grounded answers reduce hallucinations and speed evidence lookup.

It’s like a librarian who hands you the exact page, not just a summary. 📚🔎⚕️

See the retrieval pipeline and evaluation—then imagine clinic-ready tools built on top.

Paper: http://arxiv.org/abs/2510.02967v1

Register: https://www.AiFeta.com

Paper: http://arxiv.org/abs/2510.02967v1

Register: https://www.AiFeta.com

#RAG #HealthcareAI #EvidenceBased #NLP #InformationRetrieval #Guidelines #AIinMedicine

Read more

Automating GDPR Compliance: A Roadmap for Companies and Law Firms

Automating GDPR Compliance: A Roadmap for Companies and Law Firms

GDPR compliance is more than checkboxes. A new roadmap from the Privatech project shows how automation and machine learning can help companies and law firms assess—and even generate—privacy compliance. * Shift the focus to data processors’ real workflows: drafting policies, mapping data uses, documenting decisions. * Break compliance into machine-ready

FPGAs for Faster, Leaner Deep Learning: A Review of CNN Accelerators

FPGAs for Faster, Leaner Deep Learning: A Review of CNN Accelerators

Deep learning drives image search, robots, and medical scans. Most systems lean on CPUs and GPUs. This review asks: what if we run convolutional neural networks (CNNs) on FPGAs—reconfigurable chips you can tailor to the model? * Why FPGAs: custom dataflows, low latency, and strong energy efficiency—great for cameras,

Dynamic-K: Recommendations That Know When to Stop

Dynamic-K: Recommendations That Know When to Stop

Most apps show a fixed number of “top” items—say 10 movies or 20 products—assuming there are always enough good options. But that’s not always true: sometimes there are few relevant items, or some users are extra picky. The result? Filler recommendations. Dynamic-K flips the script. Instead of

Teaching chatbots to stop contradicting themselves (DECODE)

Teaching chatbots to stop contradicting themselves (DECODE)

Teaching chatbots to stop contradicting themselves Ever had a bot say one thing, then the opposite a few turns later? This study introduces DECODE—a new task and dataset for spotting contradictions in everyday conversations, drawn from both human-human and human-bot chats. * New data beats existing natural language inference (NLI)