Search papers, labs, and topics across Lattice.
This paper introduces DaV-Gen, a novel end-to-end generative retrieval framework that addresses the inconsistencies in Multi-Stage Cascade Architectures by employing a "Draft-and-Verify" mechanism. By optimizing candidate drafting and fine-grained verification simultaneously through a composite loss function, DaV-Gen enhances both the efficiency and accuracy of search and recommendation systems. The results demonstrate that this unified approach achieves the speed of sparse drafting while maintaining the precision of advanced generative models, significantly improving online serving performance.
DaV-Gen achieves the speed of traditional retrieval systems while delivering the precision of state-of-the-art generative models through its innovative Draft-and-Verify mechanism.
Mainstream industrial information retrieval systems (e.g., search and recommendation) are usually built upon Multi-Stage Cascade Architectures (MCAs), which balance effectiveness and efficiency through a coarse-to-fine ``retrieval-ranking''pipeline. However, the optimization objectives across different stages are substantially inconsistent, propagating or even amplifying the early-stage errors that ultimately degrade the quality of final results. While emerging end-to-end generative models offer a potential solution by unifying the pipeline, their online serving performance is severely hindered by the auto-regressive process inherited from the standard decoder-only structure. To bridge this gap, we introduce \textbf{DaV-Gen}, a novel unified solution designed to fundamentally refactor the paradigm for both search and recommendation via a ``Draft-and-Verify''mechanism. Inspired by the process used by speculative decoding, our framework redesigns the generation task into two synergistic operations within a single model. During training, the model is concurrently optimized for both candidate drafting and fine-grained verification. This is achieved by a composite loss function that jointly trains the model on two distinct but related objectives: 1) a contrastive loss that structures the embedding space for efficient drafting, and 2) a fusion loss that combines generative likelihood with vector similarity to produce a superior verification score. This integrated training strategy equips the model with dual capabilities. At inference time, it first performs highly efficient vector-based drafting to generate a candidate set, and then verifies these candidates using the more powerful fused scoring function, thereby achieving both the speed of sparse drafting and the precision of advanced generative models within a unified, end-to-end architecture.
