Truth Score series · Updated June 2026

AI hallucination by industry

A model's hallucination rate isn't one number — it swings from under 1.5% for summarising to 88% for legal queries. Match the model and the review process to the risk in your sector.

Quick answer. Highest risk: legal (58–88%) and medical (43–64%) without mitigation. Lowest: summarising supplied text (under 1.5%). The same model can be safe for one task in your business and dangerous for another.

Risk by sector

Sector / taskHallucination rateRequired mitigation
Legal queries & citations58–88%Verify every source; human lawyer owns output
Medical case summaries43–64%Clinical review mandatory; never autonomous
Finance & figuresHigh without toolsCalculator/code tool + human sign-off
General factual Q&A15–33%RAG + spot checks
Customer support answersModerateRAG against verified help centre
Summarising supplied text<1.5%Light review — safest use

Why some sectors are so much worse

Tasks that require recalling specific facts (case law, drug interactions, exact figures) hit the model's weakest point — it generates plausible specifics it doesn't actually know. Tasks grounded in supplied text (summarising, extracting) keep the model anchored to what's in front of it, so error rates collapse. The lesson: ground the model wherever you can.

What each sector should do

The universal fix

Across every sector, retrieval-augmented generation (RAG) is the single biggest lever — cutting hallucinations by around 71% by grounding the model in your own verified sources. Full list in how to reduce hallucinations.

Choosing a model for a high-risk sector? Favour high Truth Score models and use the match engine with safety weighted high.