IRJun 11

OneRetrieval: Unifying Multi-Branch E-commerce Retrieval with an Editable Generative Model

arXiv:2606.13533v112.6
Predicted impact top 26% in IR · last 90 daysOriginality Highly original
AI Analysis

For industrial e-commerce search, this provides the first editable generative retrieval method that can replace the inverted-index branch without sacrificing real-time term injection, solving a practical bottleneck in multi-branch retrieval systems.

OneRetrieval unifies multi-branch e-commerce retrieval into a single generative model that matches deep recall of the strongest baseline while preserving real-time editability, achieving an intervention hit rate over an order of magnitude above closed-codebook methods and significantly lifting order volume when replacing the inverted-index branch online.

Industrial e-commerce search serves hundreds of millions of items through a multi-branch retrieval stage fused by hand-tuned merging without joint optimization. Generative retrieval (GR) raises the prospect of collapsing this stage into a single model, yet unification is gated by more than retrieval quality: the inverted-index branch converts below the platform average yet persists because it is almost the only branch where operations can inject a new term within hours without any model update; a one-model substitute must preserve this real-time editability. Existing GR methods structurally lack it: closed-codebook methods fix each slot to a quantized embedding at training, while open-vocabulary methods leave new-term routing to model generalization. We present OneRetrieval, a one-model GR framework built on Keyword-Aligned Encoding (KAE), which ties each identifier position to an interpretable attribute word, pairing competitive recall quality with the editability of the inverted index -- to our knowledge the first editable generative retrieval method. An information-theoretic merging organizes 18 attribute categories into six codebook groups with non-uniform capacity; reserved slots in each codebook can be bound to new words after deployment without retraining; and a four-stage fine-tuning pipeline secures quality and editability jointly. On five million real-traffic requests, OneRetrieval matches the deep recall of the strongest generative baseline, with an intervention hit rate over an order of magnitude above closed-codebook encodings. Online, replacing the inverted-index branch significantly lifts order volume; extending to nearly the entire stage holds conversion while improving CTR. The system is deployed at Kuaishou, serving hundreds of millions of PVs daily.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes