A Survey of Model Architectures in Information Retrieval

• URL: http://arxiv.org/abs/2502.14822v2
• Date: Tue, 26 Aug 2025 23:10:28 GMT
• Title: A Survey of Model Architectures in Information Retrieval
• Authors: Zhichao Xu, Fengran Mo, Zhiqi Huang, Crystina Zhang, Puxuan Yu, Bei Wang, Jimmy Lin, Vivek Srikumar,
• Abstract summary: The period from 2019 to the present has represented one of the biggest paradigm shifts in information retrieval (IR) and natural language processing (NLP)<n>We trace the development from traditional term-based methods to modern neural approaches, particularly highlighting the impact of transformer-based models and subsequent large language models (LLMs)<n>We conclude with a forward-looking discussion of emerging challenges and future directions.
• Score: 59.61734783818073
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The period from 2019 to the present has represented one of the biggest paradigm shifts in information retrieval (IR) and natural language processing (NLP), culminating in the emergence of powerful large language models (LLMs) from 2022 onward. Methods leveraging pretrained encoder-only models (e.g., BERT) and LLMs have outperformed many previous approaches, particularly excelling in zero-shot scenarios and complex reasoning tasks. This work surveys the evolution of model architectures in IR, focusing on two key aspects: backbone models for feature extraction and end-to-end system architectures for relevance estimation. The review intentionally separates architectural considerations from training methodologies to provide a focused analysis of structural innovations in IR systems. We trace the development from traditional term-based methods to modern neural approaches, particularly highlighting the impact of transformer-based models and subsequent large language models (LLMs). We conclude with a forward-looking discussion of emerging challenges and future directions, including architectural optimizations for performance and scalability, handling of multimodal, multilingual data, and adaptation to novel application domains such as autonomous search agents that is beyond traditional search paradigms.

Related papers

• AutoMerge: Search-Based Model Merging Framework for Effective Model Reuse [8.950520457150178]
  Recently, model merging has emerged in the domain of large language models (LLMs) as a training-free approach.<n>No prior work has systematically investigated whether such an approach can be effectively applied to other deep learning models.<n>We present the first systematic study that evaluates five model merging techniques on three distinct model architectures.
  arXiv  Detail & Related papers  (2026-01-30T09:27:01Z)
• The Evolution of Reranking Models in Information Retrieval: From Heuristic Methods to Large Language Models [0.0]
  Reranking is a critical stage in information retrieval systems, improving the relevance of the user-presented final results.<n>This paper is a guide to examine the changing reranker landscape and offer a clear view of the advancements made in reranking methods.
  arXiv  Detail & Related papers  (2025-12-18T06:29:37Z)
• A Survey on Generative Recommendation: Data, Model, and Tasks [55.36322811257545]
  generative recommendation reconceptualizes recommendation as a generation task rather than discriminative scoring.<n>This survey provides a comprehensive examination through a unified tripartite framework spanning data, model, and task dimensions.<n>We identify five key advantages: world knowledge integration, natural language understanding, reasoning capabilities, scaling laws, and creative generation.
  arXiv  Detail & Related papers  (2025-10-31T04:02:58Z)
• Speed Always Wins: A Survey on Efficient Architectures for Large Language Models [51.817121227562964]
  Large Language Models (LLMs) have delivered impressive results in language understanding, generation, reasoning, and pushes the ability boundary of multimodal models.<n> Transformer models, as the foundation of modern LLMs, offer a strong baseline with excellent scaling properties.<n>The traditional transformer architecture requires substantial computations and poses significant obstacles for large-scale training and practical deployment.
  arXiv  Detail & Related papers  (2025-08-13T14:13:46Z)
• Foundation Models and Transformers for Anomaly Detection: A Survey [2.3264194695971656]
  The survey categorizes VAD methods into reconstruction-based, feature-based and zero/few-shot approaches.<n>Transformers and foundation models enable more robust, interpretable, and scalable anomaly detection solutions.
  arXiv  Detail & Related papers  (2025-07-21T12:01:04Z)
• Mixture of Experts in Large Language Models [3.1494372222592224]
  MoE architecture significantly enhances model performance while maintaining minimal computational overhead.<n>Our analysis identifies key advantages of MoE, including superior model capacity, improved task-specific performance, and the ability to scale model capacity efficiently.<n>This review outlines current research limitations, open challenges, and promising future directions, providing a foundation for continued innovation in MoE architecture and its applications.
  arXiv  Detail & Related papers  (2025-07-15T10:36:43Z)
• Continual Learning for Generative AI: From LLMs to MLLMs and Beyond [56.29231194002407]
  We present a comprehensive survey of continual learning methods for mainstream generative AI models.<n>We categorize these approaches into three paradigms: architecture-based, regularization-based, and replay-based.<n>We analyze continual learning setups for different generative models, including training objectives, benchmarks, and core backbones.
  arXiv  Detail & Related papers  (2025-06-16T02:27:25Z)
• A Survey on Mechanistic Interpretability for Multi-Modal Foundation Models [74.48084001058672]
  The rise of foundation models has transformed machine learning research.<n> multimodal foundation models (MMFMs) pose unique interpretability challenges beyond unimodal frameworks.<n>This survey explores two key aspects: (1) the adaptation of LLM interpretability methods to multimodal models and (2) understanding the mechanistic differences between unimodal language models and crossmodal systems.
  arXiv  Detail & Related papers  (2025-02-22T20:55:26Z)
• Generalized Factor Neural Network Model for High-dimensional Regression [50.554377879576066]
  We tackle the challenges of modeling high-dimensional data sets with latent low-dimensional structures hidden within complex, non-linear, and noisy relationships.<n>Our approach enables a seamless integration of concepts from non-parametric regression, factor models, and neural networks for high-dimensional regression.
  arXiv  Detail & Related papers  (2025-02-16T23:13:55Z)
• Redefining Data-Centric Design: A New Approach with a Domain Model and Core Data Ontology for Computational Systems [2.872069347343959]
  This paper presents an innovative data-centric paradigm for designing computational systems by introducing a new informatics domain model. The proposed model moves away from the conventional node-centric framework and focuses on data-centric categorization, using a multimodal approach that incorporates objects, events, concepts, and actions.
  arXiv  Detail & Related papers  (2024-09-01T22:34:12Z)
• Vision Foundation Models in Remote Sensing: A Survey [6.036426846159163]
  Foundation models are large-scale, pre-trained AI models capable of performing a wide array of tasks with unprecedented accuracy and efficiency.<n>This survey aims to serve as a resource for researchers and practitioners by providing a panorama of advances and promising pathways for continued development and application of foundation models in remote sensing.
  arXiv  Detail & Related papers  (2024-08-06T22:39:34Z)
• iNNspector: Visual, Interactive Deep Model Debugging [8.997568393450768]
  We propose a conceptual framework structuring the data space of deep learning experiments. Our framework captures design dimensions and proposes mechanisms to make this data explorable and tractable. We present the iNNspector system, which enables tracking of deep learning experiments and provides interactive visualizations of the data.
  arXiv  Detail & Related papers  (2024-07-25T12:48:41Z)
• Retrieval-Enhanced Machine Learning: Synthesis and Opportunities [60.34182805429511]
  Retrieval-enhancement can be extended to a broader spectrum of machine learning (ML) This work introduces a formal framework of this paradigm, Retrieval-Enhanced Machine Learning (REML), by synthesizing the literature in various domains in ML with consistent notations which is missing from the current literature. The goal of this work is to equip researchers across various disciplines with a comprehensive, formally structured framework of retrieval-enhanced models, thereby fostering interdisciplinary future research.
  arXiv  Detail & Related papers  (2024-07-17T20:01:21Z)
• Generalist Multimodal AI: A Review of Architectures, Challenges and Opportunities [5.22475289121031]
  Multimodal models are expected to be a critical component to future advances in artificial intelligence. This work provides a fresh perspective on generalist multimodal models via a novel architecture and training configuration specific taxonomy.
  arXiv  Detail & Related papers  (2024-06-08T15:30:46Z)
• The Buffer Mechanism for Multi-Step Information Reasoning in Language Models [52.77133661679439]
  Investigating internal reasoning mechanisms of large language models can help us design better model architectures and training strategies. In this study, we constructed a symbolic dataset to investigate the mechanisms by which Transformer models employ vertical thinking strategy. We proposed a random matrix-based algorithm to enhance the model's reasoning ability, resulting in a 75% reduction in the training time required for the GPT-2 model.
  arXiv  Detail & Related papers  (2024-05-24T07:41:26Z)
• Machine learning for structural design models of continuous beam systems via influence zones [3.284878354988896]
  This work develops a machine learned structural design model for continuous beam systems from the inverse problem perspective. The aim of this approach is to conceptualise a non-iterative structural design model that predicts cross-section requirements for continuous beam systems of arbitrary system size.
  arXiv  Detail & Related papers  (2024-03-14T14:53:18Z)
• ZhiJian: A Unifying and Rapidly Deployable Toolbox for Pre-trained Model Reuse [59.500060790983994]
  This paper introduces ZhiJian, a comprehensive and user-friendly toolbox for model reuse, utilizing the PyTorch backend. ZhiJian presents a novel paradigm that unifies diverse perspectives on model reuse, encompassing target architecture construction with PTM, tuning target model with PTM, and PTM-based inference.
  arXiv  Detail & Related papers  (2023-08-17T19:12:13Z)
• Model-Based Deep Learning [155.063817656602]
  Signal processing, communications, and control have traditionally relied on classical statistical modeling techniques. Deep neural networks (DNNs) use generic architectures which learn to operate from data, and demonstrate excellent performance. We are interested in hybrid techniques that combine principled mathematical models with data-driven systems to benefit from the advantages of both approaches.
  arXiv  Detail & Related papers  (2020-12-15T16:29:49Z)
• Neural Entity Linking: A Survey of Models Based on Deep Learning [82.43751915717225]
  This survey presents a comprehensive description of recent neural entity linking (EL) systems developed since 2015. Its goal is to systemize design features of neural entity linking systems and compare their performance to the remarkable classic methods on common benchmarks. The survey touches on applications of entity linking, focusing on the recently emerged use-case of enhancing deep pre-trained masked language models.
  arXiv  Detail & Related papers  (2020-05-31T18:02:26Z)

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.