发表机构
Lunit（鲁尼特）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究临床检索增强生成中的欺骗性基础问题，通过对13个模型测试发现DG率8%-87%，医学等微调模型高达86.7%。控制消融确定机制，实体归因验证可检测DG，现有框架未实施，为该领域研究提供新视角和方法。
AI 中文摘要
检索增强生成评估检查模型声明是否在检索到的文档中有事实依据，但不检查检索到的证据是否归因于正确的实体。临床RAG响应可能通过所有自动检查，但将药物Y的临床证据呈现为关于查询药物X的证据，即欺骗性基础（DG）。通过对13个模型的控制因子基准测试，发现对抗条件下DG率在8%-87%之间。医学和生物医学微调模型高达86.7%，领域专业化加剧了失败。控制消融确定了机制，去除检索文档中特定实体的临床证据可消除实体归因失败。在部署的RAG系统中，740个药物-疾病对的生产测量发现总体DG为7.8%，新批准药物升至13.6%。实体归因验证检测DG的精度为97.0%，召回率为98.7%，现有框架未实施。
英文摘要
Retrieval-augmented generation evaluation checks whether model claims are factually grounded in retrieved documents. It does not check whether retrieved evidence is attributed to the correct entity. A clinical RAG response can pass every automated check (zero hallucinations, near-perfect faithfulness, real citations) while presenting drug Y's clinical evidence as evidence about queried drug X. We term this deceptive grounding (DG): a failure invisible to faithfulness, hallucination, and citation checks because every claim is sourced from a real document, about the wrong entity. Using a controlled factorial benchmark across 13 models, we find DG rates spanning 8-87% at peak adversarial conditions. Medical and biomedical fine-tuned models reach up to 86.7%; domain specialization amplifies the failure rather than mitigating it. A controlled ablation identifies the mechanism: removing entity-specific clinical evidence from retrieved documents eliminates entity-attribution failure entirely, shifting all failures to confabulation. The two failure modes respond to the same trigger, taking different paths. Production measurement across 740 drug-disease pairs finds 7.8% overall DG in a deployed RAG system, rising to 13.6% for recently approved drugs. Entity-attribution verification (checking that cited evidence applies to the queried entity) detects DG at 97.0% precision and 98.7% DG recall (IPW-adjusted human gold standard); no existing framework implements it.
Comments24 pages, 7 figures, 12 tables
