タグ：hallucination-detection

Use Jev instead of an LLM for RAG decisions: relevance grading, query routing, hallucination checks and LLM-as-a-judge evals. Faster, cheaper, measured first.

RAG evaluation with typed decisions: sentence-level hallucination verdicts with offsets and citations, passage and answer relevance, in one Jev call per answer. Benchmarked against Ragas, DeepEval, an LLM judge and HHEM.

Can a non-generative model (Jev) double-check an AI scribe's note against the encounter transcript? Working mock-up, psychiatry encounter, colour-coded draft with click-to-source and omission flags.