Retrieving Support to Rank Answers in Open-Domain Question Answering

AbstractWe introduce a novel Question Answering (QA) architecture that enhances answer selection by retrieving targeted supporting evidence. Unlike traditional methods, which retrieve documents or passages relevant only to a query q, our approach retrieves content relevant to the combined pair (q, a), explicitly emphasizing the supporting relation between the query and a candidate answer a. By prioritizing this relational context, our model effectively identifies paragraphs that directly substantiate the correctness of a with respect to q, leading to more accurate answer verification than standard retrieval systems. Our neural retrieval method also scales efficiently to collections containing hundreds of millions of paragraphs. Moreover, this approach can be used by large language models (LLMs) to retrieve explanatory paragraphs that ground their reasoning, enabling them to tackle more complex QA tasks with greater reliability and interpretability.