Ruling Out to Rule In: Contrastive Hypothesis Retrieval for Medical Question Answering

ArXi:2604.04593v1 Announce Type: cross 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.