English
Related papers

Related papers: Learning to Tokenize for Generative Retrieval

200 papers

This paper introduces PAG-a novel optimization and decoding approach that guides autoregressive generation of document identifiers in generative retrieval models through simultaneous decoding. To this aim, PAG constructs a set-based and…

Information Retrieval · Computer Science 2024-04-24 Hansi Zeng , Chen Luo , Hamed Zamani

Generative retrieval-based recommendation has emerged as a promising paradigm aiming at directly generating the identifiers of the target candidates. However, in large-scale recommendation systems, this approach becomes increasingly…

Information Retrieval · Computer Science 2025-06-23 Penglong Zhai , Yifang Yuan , Fanyi Di , Jie Li , Yue Liu , Chen Li , Jie Huang , Sicong Wang , Yao Xu , Xin Li

Generative retrieval directly decode a document identifier (i.e., docid) in response to a query, making it impossible to provide users with explanations as an answer for ``why is this document retrieved?''. To address this limitation, we…

Information Retrieval · Computer Science 2026-04-14 Sangam Lee , Ryang Heo , SeongKu Kang , Susik Yoon , Jinyoung Yeo , Dongha Lee

Generative retrieval introduces a groundbreaking paradigm to document retrieval by directly generating the identifier of a pertinent document in response to a specific query. This paradigm has demonstrated considerable benefits and…

Information Retrieval · Computer Science 2024-10-28 Mingming Li , Huimu Wang , Zuxu Chen , Guangtao Nie , Yiming Qiu , Guoyu Tang , Lin Liu , Jingwei Zhuo

We apply an information-theoretic perspective to reconsider generative document retrieval (GDR), in which a document $x \in X$ is indexed by $t \in T$, and a neural autoregressive model is trained to map queries $Q$ to $T$. GDR can be…

Information Retrieval · Computer Science 2024-05-22 Xin Du , Lixin Xiu , Kumiko Tanaka-Ishii

Generative document retrieval, an emerging paradigm in information retrieval, learns to build connections between documents and identifiers within a single model, garnering significant attention. However, there are still two challenges: (1)…

Information Retrieval · Computer Science 2024-05-14 Yong Guan , Dingxiao Liu , Jinchen Ma , Hao Peng , Xiaozhi Wang , Lei Hou , Ru Li

Document retrieval techniques are essential for developing large-scale information systems. The common approach involves using a bi-encoder to compute the semantic similarity between a query and documents. However, the scalar similarity…

Information Retrieval · Computer Science 2025-06-02 Haoyu Liu , Shaohan Huang , Jianfeng Liu , Yuefeng Zhan , Hao Sun , Weiwei Deng , Feng Sun , Furu Wei , Qi Zhang

In web environments, user preferences are often refined progressively as users move from browsing broad categories to exploring specific items. However, existing generative recommenders overlook this natural refinement process. Generative…

Information Retrieval · Computer Science 2025-12-01 Tianxin Wei , Xuying Ning , Xuxing Chen , Ruizhong Qiu , Yupeng Hou , Yan Xie , Shuang Yang , Zhigang Hua , Jingrui He

Generative retrieval is a promising new neural retrieval paradigm that aims to optimize the retrieval pipeline by performing both indexing and retrieval with a single transformer model. However, this new paradigm faces challenges with…

Information Retrieval · Computer Science 2023-06-21 Thong Nguyen , Andrew Yates

Generative recommendation systems have gained increasing attention as an innovative approach that directly generates item identifiers for recommendation tasks. Despite their potential, a major challenge is the effective construction of item…

Information Retrieval · Computer Science 2025-06-05 Enze Liu , Bowen Zheng , Cheng Ling , Lantao Hu , Han Li , Wayne Xin Zhao

Generative retrieval (GR) is an emerging paradigm that leverages large language models (LLMs) to autoregressively generate document identifiers (docids) relevant to a given query. Prior works have focused on leveraging the generative…

Information Retrieval · Computer Science 2025-10-22 Yingchen Zhang , Ruqing Zhang , Jiafeng Guo , Wenjun Peng , Sen Li , Fuyu Lv

Standard language models generate text by selecting tokens from a fixed, finite, and standalone vocabulary. We introduce a novel method that selects context-aware phrases from a collection of supporting documents. One of the most…

Computation and Language · Computer Science 2024-03-19 Bowen Cao , Deng Cai , Leyang Cui , Xuxin Cheng , Wei Bi , Yuexian Zou , Shuming Shi

Document reconstruction constitutes a significant facet of document analysis and recognition, a field that has been progressively accruing interest within the scholarly community. A multitude of these researchers employ an array of document…

Computer Vision and Pattern Recognition · Computer Science 2025-07-09 Xin Li , Mingming Gong , Yunfei Wu , Jianxin Dai , Antai Guo , Xinghua Jiang , Haoyu Cao , Yinsong Liu , Deqiang Jiang , Xing Sun

Generative Retrieval (GR), autoregressively decoding relevant document identifiers given a query, has been shown to perform well under the setting of small-scale corpora. By memorizing the document corpus with model parameters, GR…

Information Retrieval · Computer Science 2024-01-22 Peiwen Yuan , Xinglin Wang , Shaoxiong Feng , Boyuan Pan , Yiwei Li , Heda Wang , Xupeng Miao , Kan Li

Instead of simply matching a query to pre-existing passages, generative retrieval generates identifier strings of passages as the retrieval target. At a cost, the identifier must be distinctive enough to represent a passage. Current…

Computation and Language · Computer Science 2023-05-29 Yongqi Li , Nan Yang , Liang Wang , Furu Wei , Wenjie Li

Document retrieval has been extensively studied within the index-retrieve framework for decades, which has withstood the test of time. Unfortunately, such a pipelined framework limits the optimization of the final retrieval quality, because…

Information Retrieval · Computer Science 2022-08-22 Yujia Zhou , Jing Yao , Zhicheng Dou , Ledell Wu , Peitian Zhang , Ji-Rong Wen

BERT based ranking models have achieved superior performance on various information retrieval tasks. However, the large number of parameters and complex self-attention operation come at a significant latency overhead. To remedy this, recent…

Information Retrieval · Computer Science 2021-10-06 Nachshon Cohen , Amit Portnoy , Besnik Fetahu , Amir Ingber

Document-level Relation Triplet Extraction (DocRTE) is a fundamental task in information systems that aims to simultaneously extract entities with semantic relations from a document. Existing methods heavily rely on a substantial amount of…

Computation and Language · Computer Science 2024-01-25 Qi Sun , Kun Huang , Xiaocui Yang , Rong Tong , Kun Zhang , Soujanya Poria

Understanding complex multimodal documents remains challenging due to their structural inconsistencies and limited training data availability. We introduce \textit{DocsRay}, a training-free document understanding system that integrates…

Machine Learning · Computer Science 2025-08-01 Hyeon Seong Jeong , Sangwoo Jo , Byeong Hyun Yoon , Yoonseok Heo , Haedong Jeong , Taehoon Kim

Layout is a fundamental component of any graphic design. Creating large varieties of plausible document layouts can be a tedious task, requiring numerous constraints to be satisfied, including local ones relating different semantic elements…

Computer Vision and Pattern Recognition · Computer Science 2020-04-20 Akshay Gadi Patil , Omri Ben-Eliezer , Or Perel , Hadar Averbuch-Elor