Towards Dynamic Dense Retrieval with Routing Strategy

• URL: http://arxiv.org/abs/2602.22547v1
• Date: Thu, 26 Feb 2026 02:38:40 GMT
• Title: Towards Dynamic Dense Retrieval with Routing Strategy
• Authors: Zhan Su, Fengran Mo, Jinghan Zhang, Yuchen Hui, Jia Ao Sun, Bingbing Wen, Jian-Yun Nie,
• Abstract summary: We propose a novel dense retrieval approach, termed textitdynamic dense retrieval ( DDR)<n> DDR uses textit tuning as a textit module specialized for a specific domain. These modules can then be compositional combined with a dynamic routing strategy, enabling highly flexible domain adaptation in the retrieval part.<n>Extensive evaluation on six zero-shot downstream tasks demonstrates that this approach can surpass DR while utilizing only 2% of the training parameters, paving the way to achieve more flexible dense retrieval in IR.
• Score: 24.128232978517076
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The \textit{de facto} paradigm for applying dense retrieval (DR) to new tasks involves fine-tuning a pre-trained model for a specific task. However, this paradigm has two significant limitations: (1) It is difficult adapt the DR to a new domain if the training dataset is limited. (2) Old DR models are simply replaced by newer models that are trained from scratch when the former are no longer up to date. Especially for scenarios where the model needs to be updated frequently, this paradigm is prohibitively expensive. To address these challenges, we propose a novel dense retrieval approach, termed \textit{dynamic dense retrieval} (DDR). DDR uses \textit{prefix tuning} as a \textit{module} specialized for a specific domain. These modules can then be compositional combined with a dynamic routing strategy, enabling highly flexible domain adaptation in the retrieval part. Extensive evaluation on six zero-shot downstream tasks demonstrates that this approach can surpass DR while utilizing only 2\% of the training parameters, paving the way to achieve more flexible dense retrieval in IR. We see it as a promising future direction for applying dense retrieval to various tasks.

Related papers

• GLASS: A Generative Recommender for Long-sequence Modeling via SID-Tier and Semantic Search [51.44490997013772]
  GLASS is a novel framework that integrates long-term user interests into the generative process via SID-Tier and Semantic Search.<n>We show that GLASS outperforms state-of-the-art baselines in experiments on two large-scale real-world datasets.
  arXiv  Detail & Related papers  (2026-02-05T13:48:33Z)
• SitEmb-v1.5: Improved Context-Aware Dense Retrieval for Semantic Association and Long Story Comprehension [77.93156509994994]
  We show how to represent short chunks in a way that is conditioned on a broader context window to enhance retrieval performance.<n>Existing embedding models are not well-equipped to encode such situated context effectively.<n>Our method substantially outperforms state-of-the-art embedding models.
  arXiv  Detail & Related papers  (2025-08-03T23:59:31Z)
• UniSTD: Towards Unified Spatio-Temporal Learning across Diverse Disciplines [64.84631333071728]
  We introduce bfUnistage, a unified Transformer-based framework fortemporal modeling.<n>Our work demonstrates that a task-specific vision-text can build a generalizable model fortemporal learning.<n>We also introduce a temporal module to incorporate temporal dynamics explicitly.
  arXiv  Detail & Related papers  (2025-03-26T17:33:23Z)
• Birdie: Advancing State Space Models with Reward-Driven Objectives and Curricula [23.071384759427072]
  State space models (SSMs) offer advantages over Transformers but struggle with tasks requiring long-range in-context retrieval-like text copying, associative recall, and question answering over long contexts.<n>We propose a novel training procedure, Birdie, that significantly enhances the in-context retrieval capabilities of SSMs without altering their architecture.
  arXiv  Detail & Related papers  (2024-11-01T21:01:13Z)
• Frequency Disentangled Learning for Segmentation of Midbrain Structures from Quantitative Susceptibility Mapping Data [1.9150304734969674]
  Deep models tend to fit the target function from low to high frequencies. One often lacks sufficient samples for training deep segmentation models. We propose a new training method based on frequency-domain disentanglement.
  arXiv  Detail & Related papers  (2023-02-25T04:30:11Z)
• DPTDR: Deep Prompt Tuning for Dense Passage Retrieval [53.217524851268216]
  Deep prompt tuning (DPT) has gained great success in most natural language processing(NLP) tasks. However, it is not well-investigated in dense retrieval where fine-tuning(FT) still dominates. We propose two model-agnostic and task-agnostic strategies for DPT-based retrievers, namely retrieval-oriented intermediate pretraining and unified negative mining.
  arXiv  Detail & Related papers  (2022-08-24T12:55:00Z)
• Disentangled Modeling of Domain and Relevance for Adaptable Dense Retrieval [54.349418995689284]
  We propose a novel Dense Retrieval (DR) framework named Disentangled Dense Retrieval ( DDR) to support effective domain adaptation for DR models. By making the REM and DAMs disentangled, DDR enables a flexible training paradigm in which REM is trained with supervision once and DAMs are trained with unsupervised data. DDR significantly improves ranking performance compared to strong DR baselines and substantially outperforms traditional retrieval methods in most scenarios.
  arXiv  Detail & Related papers  (2022-08-11T11:18:50Z)
• Retrieve-and-Fill for Scenario-based Task-Oriented Semantic Parsing [110.4684789199555]
  We introduce scenario-based semantic parsing: a variant of the original task which first requires disambiguating an utterance's "scenario" This formulation enables us to isolate coarse-grained and fine-grained aspects of the task, each of which we solve with off-the-shelf neural modules. Our model is modular, differentiable, interpretable, and allows us to garner extra supervision from scenarios.
  arXiv  Detail & Related papers  (2022-02-02T08:00:21Z)
• Bilevel Online Adaptation for Out-of-Domain Human Mesh Reconstruction [94.25865526414717]
  This paper considers a new problem of adapting a pre-trained model of human mesh reconstruction to out-of-domain streaming videos. We propose Bilevel Online Adaptation, which divides the optimization process of overall multi-objective into two steps of weight probe and weight update in a training. We demonstrate that BOA leads to state-of-the-art results on two human mesh reconstruction benchmarks.
  arXiv  Detail & Related papers  (2021-03-30T15:47:58Z)
• Lifelong Learning Without a Task Oracle [13.331659934508764]
  Supervised deep neural networks are known to undergo a sharp decline in the accuracy of older tasks when new tasks are learned. We propose and compare several candidate task-assigning mappers which require very little memory overhead. Best-performing variants only impose an average cost of 1.7% parameter memory increase.
  arXiv  Detail & Related papers  (2020-11-09T21:30:31Z)
• Low-Resource Domain Adaptation for Compositional Task-Oriented Semantic Parsing [85.35582118010608]
  Task-oriented semantic parsing is a critical component of virtual assistants. Recent advances in deep learning have enabled several approaches to successfully parse more complex queries. We propose a novel method that outperforms a supervised neural model at a 10-fold data reduction.
  arXiv  Detail & Related papers  (2020-10-07T17:47:53Z)
• Zero-shot Neural Passage Retrieval via Domain-targeted Synthetic Question Generation [10.324402925019946]
  A major obstacle to the wide-spread adoption of neural retrieval models is that they require large supervised training sets to surpass traditional term-based techniques. In this paper, we propose an approach to zero-shot learning for passage retrieval that uses synthetic question generation to close this gap.
  arXiv  Detail & Related papers  (2020-04-29T22:21:31Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.