deceptive-grounding-04040fe8·1 events·first seen Aliases: deceptive grounding
A new arXiv paper identifies 'deceptive grounding' (DG), a failure mode in clinical retrieval-augmented generation where a model presents evidence about drug Y as evidence about queried drug X, passing all standard faithfulness, hallucination, and citation checks. Using a controlled factorial benchmark across 13 models, the authors find DG rates of 8–87% under adversarial conditions, with medical fine-tuned models reaching 86.7%—worse than general models. A production measurement across 740 drug-disease pairs finds 7.8% overall DG in a deployed system, rising to 13.6% for recently approved drugs. The paper proposes entity-attribution verification as a mitigation, achieving 97.0% precision and 98.7% recall, and notes no existing RAG evaluation framework implements this check.