RAG fine tuning may cut retrieval accuracy by 40% and break agent decisions at scale

Precision training can still worsen meaning detection

Redis research warns that fine-tuning RAG embedding models for “compositional sensitivity” can quietly harm general retrieval, dropping accuracy up to 40% on production mid-size models. The issue: structural meaning shifts like negation and role reversals can end up near-identical in embedding space, while common fine-tuning metrics miss it. Agentic pipelines are especially vulnerable.