{"type":"ScholarlyArticle","title":"DaV-Gen: End-to-End Generative Retrieval via Draft-and-Verify","authors":[{"name":"Meng Zhao","slug":"meng-zhao","given":"Meng","family":"Zhao","affiliation":""},{"name":"Chunmei Liu","slug":"chunmei-liu","given":"Chunmei","family":"Liu","affiliation":""},{"name":"Qinyong Wang","slug":"qinyong-wang","given":"Qinyong","family":"Wang","affiliation":""}],"abstract":"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.\r\n\r\nTo bridge this gap, we introduce 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.","doi":"10.24963/ijcai.2026/363","url":"https://ijcai.org/proceedings/2026/363","pdf":"https://ijcai.org/proceedings/2026/0363.pdf","markdown":"https://ijcai.org/proceedings/2026/363.md","bibtex":"https://ijcai.org/proceedings/2026/bibtex/363","volume":{"slug":"2026","title":"Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2026","url":"https://ijcai.org/proceedings/2026/","year":2026,"location":"Bremen, Germany","dates":"15-21 August 2026","editors":"Diego Calvanese","isbn":"978-1-956792-09-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2026"},"section":"Data Mining","track":"Main Track","number":363,"pages":{"first":3268,"last":3275},"keywords":["Natural Language Processing: Language generation","Data Mining: Collaborative filtering","Data Mining: Recommender systems"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}