Retrieval-augmented generation (RAG) grounds large language models in external medical knowledge, yet standard retrievers frequently surface hard negatives that are semantically close to the query but describe clinically distinct conditions. While existing query-expansion methods improve query representation to mitigate ambiguity, they typically focus on enriching target-relevant semantics without an explicit mechanism to selectively suppress specific, clinically plausible hard negatives. This leaves the system prone to retrieving plausible mimics that overshadow the actual diagnosis, particularly when such mimics are dominant within the corpus. We propose Contrastive Hypothesis Retrieval (CHR), a framework inspired by the process of clinical differential diagnosis. CHR generates a target hypothesis $H^+$ for the likely correct answer and a mimic hypothesis $H^-$ for the most plausible incorrect alternative, then scores documents by promoting $H^+$-aligned evidence while penalizing $H^-$-aligned content. Across three medical QA benchmarks and three answer generators, CHR outperforms all five baselines in every configuration, with improvements of up to 10.4 percentage points over the next-best method. On the $n=587$ pooled cases where CHR answers correctly while embedded hypothetical-document query expansion does not, 85.2\% have no shared documents between the top-5 retrieval lists of CHR and of that baseline, consistent with substantive retrieval redirection rather than light re-ranking of the same candidates. By explicitly modeling what to avoid alongside what to find, CHR bridges clinical reasoning with retrieval mechanism design and offers a practical path to reducing hard-negative contamination in medical RAG systems.

翻译：检索增强生成（RAG）将大型语言模型锚定到外部医学知识中，然而标准检索器经常返回与查询语义接近但描述临床上不同病症的困难负样本。现有查询扩展方法虽能改进查询表示以缓解歧义，但通常侧重于丰富目标相关语义，缺乏明确机制选择性抑制特定、临床上合理的困难负样本。这使得系统易检索到掩盖实际诊断的合理近似病变，尤其是在语料库中此类近似病变占主导地位时。受临床鉴别诊断过程启发，我们提出对比假设检索（CHR）框架。CHR生成针对可能正确答案的目标假设$H^+$与针对最可能错误备选答案的模仿假设$H^-$，通过促进与$H^+$对齐的证据同时惩罚与$H^-$对齐的内容来对文档进行评分。在三个医学问答基准测试和三个答案生成器上，CHR在所有配置中均优于五种基线方法，相较于次优方法性能提升高达10.4个百分点。在CHR正确回答而嵌入假设文档查询扩展未能回答的$n=587$个汇集案例中，85.2%的案例中CHR与基线的前5位检索列表无共享文档，这表明实质性的检索重定向而非对相同候选项的简单重排序。通过明确建模"该避免什么"与"该寻找什么"，CHR架起了临床推理与检索机制设计的桥梁，为减少医学RAG系统中的困难负样本污染提供了实用路径。