Efficient Rationale-based Retrieval: On-policy Distillation from Generative Rerankers based on JEPA

ArXi:2604.23336v1 Announce Type: cross Unlike traditional fact-based retrieval, rationale-based retrieval typically necessitates cross-encoding of query-document pairs using large language models, incurring substantial computational costs. To address this limitation, we propose Rabtriever, which independently encodes queries and documents, while providing comparable cross query-document comprehension capabilities to rerankers. We start from