Revela: Dense Retriever Learning via Language Modeling (2506.16552v1)

Abstract: Dense retrievers play a vital role in accessing external and specialized knowledge to augment LMs. Training dense retrievers typically requires annotated query-document pairs, which are costly and hard to obtain in specialized domains such as code-motivating growing interest in self-supervised retriever learning. Since LMs are trained to capture token-level dependencies through a self-supervised learning objective (i.e., next-token prediction), we can analogously cast retrieval as learning dependencies among chunks of tokens. This analogy naturally leads to the question: How can we adapt self-supervised learning objectives in the spirit of LLMing to train retrievers? To answer this question, we introduce Revela, a unified and scalable training framework for self-supervised retriever learning via LLMing. Revela models semantic dependencies among documents by conditioning next-token prediction on both local and cross-document context through an in-batch attention mechanism. This attention is weighted by retriever-computed similarity scores, enabling the retriever to be optimized as part of LLMing. We evaluate Revela on both general-domain (BEIR) and domain-specific (CoIR) benchmarks across various retriever backbones. At a comparable parameter scale, Revela outperforms the previous best method with absolute improvements of 5.2 % (18.3 % relative) and 5.6 % (14.4 % relative) on NDCG@10, respectively, underscoring its effectiveness. Performance increases with model size, highlighting both the scalability of our approach and its promise for self-supervised retriever learning.