Saved in:
Bibliographic Details
Main Authors: Zhao, Xinpeng, Ren, Zhaochun, Zhao, Yukun, Li, Zhenyang, Zhang, Mengqi, Feng, Jun, Chen, Ran, Zhou, Ying, Chen, Zhumin, Wang, Shuaiqiang, Yin, Dawei, Xin, Xin
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2511.08150
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912870014386176
author Zhao, Xinpeng
Ren, Zhaochun
Zhao, Yukun
Li, Zhenyang
Zhang, Mengqi
Feng, Jun
Chen, Ran
Zhou, Ying
Chen, Zhumin
Wang, Shuaiqiang
Yin, Dawei
Xin, Xin
author_facet Zhao, Xinpeng
Ren, Zhaochun
Zhao, Yukun
Li, Zhenyang
Zhang, Mengqi
Feng, Jun
Chen, Ran
Zhou, Ying
Chen, Zhumin
Wang, Shuaiqiang
Yin, Dawei
Xin, Xin
contents Generative retrieval (GR) reframes document retrieval as an end-to-end task of generating sequential document identifiers (DocIDs). Existing GR methods predominantly rely on left-to-right auto-regressive decoding, which suffers from two fundamental limitations: (i) a \emph{mismatch between DocID generation and natural language generation}, whereby an incorrect DocID token generated at an early step can lead to entirely erroneous retrieval; and (ii) an \emph{inability to dynamically balance the trade-off between retrieval efficiency and accuracy}, which is crucial for practical applications. To tackle these challenges, we propose generative document retrieval with diffusion language models, termed \emph{DiffuGR}. DiffuGR formulates DocID generation as a discrete diffusion process. During training, DocIDs are corrupted through a stochastic masking process, and a diffusion language model is trained to recover them under a retrieval-aware objective. For inference, DiffuGR generates DocID tokens in parallel and refines them through a controllable number of denoising steps. Unlike auto-regressive decoding, DiffuGR introduce \emph{a novel mechanism to first generate plenty of confident DocID tokens and then refine the generation through diffusion-based denoising}. Moreover, DiffuGR also offers \emph{explicit runtime control over the quality-latency tradeoff}. Extensive experiments on widely-applied retrieval benchmarks show that DiffuGR outperforms strong auto-regressive generative retrievers. Additionally, we verify that DiffuGR achieves flexible control over the quality-latency trade-off via variable denoising budgets.
format Preprint
id arxiv_https___arxiv_org_abs_2511_08150
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DiffuGR: Generative Document Retrieval with Diffusion Language Models
Zhao, Xinpeng
Ren, Zhaochun
Zhao, Yukun
Li, Zhenyang
Zhang, Mengqi
Feng, Jun
Chen, Ran
Zhou, Ying
Chen, Zhumin
Wang, Shuaiqiang
Yin, Dawei
Xin, Xin
Information Retrieval
Generative retrieval (GR) reframes document retrieval as an end-to-end task of generating sequential document identifiers (DocIDs). Existing GR methods predominantly rely on left-to-right auto-regressive decoding, which suffers from two fundamental limitations: (i) a \emph{mismatch between DocID generation and natural language generation}, whereby an incorrect DocID token generated at an early step can lead to entirely erroneous retrieval; and (ii) an \emph{inability to dynamically balance the trade-off between retrieval efficiency and accuracy}, which is crucial for practical applications. To tackle these challenges, we propose generative document retrieval with diffusion language models, termed \emph{DiffuGR}. DiffuGR formulates DocID generation as a discrete diffusion process. During training, DocIDs are corrupted through a stochastic masking process, and a diffusion language model is trained to recover them under a retrieval-aware objective. For inference, DiffuGR generates DocID tokens in parallel and refines them through a controllable number of denoising steps. Unlike auto-regressive decoding, DiffuGR introduce \emph{a novel mechanism to first generate plenty of confident DocID tokens and then refine the generation through diffusion-based denoising}. Moreover, DiffuGR also offers \emph{explicit runtime control over the quality-latency tradeoff}. Extensive experiments on widely-applied retrieval benchmarks show that DiffuGR outperforms strong auto-regressive generative retrievers. Additionally, we verify that DiffuGR achieves flexible control over the quality-latency trade-off via variable denoising budgets.
title DiffuGR: Generative Document Retrieval with Diffusion Language Models
topic Information Retrieval
url https://arxiv.org/abs/2511.08150