QDER: Query-Specific Document and Entity Representations for Multi-Vector Document Re-Ranking

• URL: http://arxiv.org/abs/2510.11589v1
• Date: Mon, 13 Oct 2025 16:31:06 GMT
• Title: QDER: Query-Specific Document and Entity Representations for Multi-Vector Document Re-Ranking
• Authors: Shubham Chatterjee, Jeff Dalton,
• Abstract summary: We introduce QDER, a neural re-ranking model that unifies approaches by integrating knowledge graph semantics into a multi-vector model.<n>QDER's key innovation lies in its modeling of query-document relationships.<n>We first transform these fine-grained representations through learned attention patterns, then apply carefully chosen mathematical operations for precise matches.
• Score: 5.469844680867749
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Neural IR has advanced through two distinct paths: entity-oriented approaches leveraging knowledge graphs and multi-vector models capturing fine-grained semantics. We introduce QDER, a neural re-ranking model that unifies these approaches by integrating knowledge graph semantics into a multi-vector model. QDER's key innovation lies in its modeling of query-document relationships: rather than computing similarity scores on aggregated embeddings, we maintain individual token and entity representations throughout the ranking process, performing aggregation only at the final scoring stage - an approach we call "late aggregation." We first transform these fine-grained representations through learned attention patterns, then apply carefully chosen mathematical operations for precise matches. Experiments across five standard benchmarks show that QDER achieves significant performance gains, with improvements of 36% in nDCG@20 over the strongest baseline on TREC Robust 2004 and similar improvements on other datasets. QDER particularly excels on difficult queries, achieving an nDCG@20 of 0.70 where traditional approaches fail completely (nDCG@20 = 0.0), setting a foundation for future work in entity-aware retrieval.

Related papers

• CIR-CoT: Towards Interpretable Composed Image Retrieval via End-to-End Chain-of-Thought Reasoning [93.05917922306196]
  Composed Image Retrieval (CIR) aims to find a target image from a reference image and a modification text.<n>CIR-CoT is the first end-to-end retrieval-oriented MLLM designed to integrate explicit Chain-of-Thought (CoT) reasoning.
  arXiv  Detail & Related papers  (2025-10-09T09:41:45Z)
• CoT Referring: Improving Referring Expression Tasks with Grounded Reasoning [67.18702329644526]
  CoT Referring enhances model reasoning across modalities through a structured, chain-of-thought training data structure.<n>We restructure the training data to enforce a new output form, providing new annotations for existing datasets.<n>We also integrate detection and segmentation capabilities into a unified MLLM framework, training it with a novel adaptive weighted loss to optimize performance.
  arXiv  Detail & Related papers  (2025-10-03T08:50:21Z)
• A Query-Aware Multi-Path Knowledge Graph Fusion Approach for Enhancing Retrieval-Augmented Generation in Large Language Models [3.0748861313823]
  QMKGF is a Query-Aware Multi-Path Knowledge Graph Fusion Approach for Enhancing Retrieval Augmented Generation.<n>We design prompt templates and employ general-purpose LLMs to extract entities and relations.<n>We introduce a multi-path subgraph construction strategy that incorporates one-hop relations, multi-hop relations, and importance-based relations.
  arXiv  Detail & Related papers  (2025-07-07T02:22:54Z)
• Query-Based Adaptive Aggregation for Multi-Dataset Joint Training Toward Universal Visual Place Recognition [10.8843105310375]
  Query-based Adaptive Aggregation (QAA) is a novel feature aggregation technique that leverages learned queries as reference codebooks.<n>We show that QAA outperforms state-of-the-art models, achieving balanced generalization across diverse datasets while maintaining peak performance comparable to dataset-specific models.
  arXiv  Detail & Related papers  (2025-07-04T22:40:03Z)
• Universal Retrieval for Multimodal Trajectory Modeling [12.160448446091607]
  Trajectory data holds significant potential for enhancing AI agent capabilities.<n>We introduce Multimodal Trajectory Retrieval, bridging the gap between universal retrieval and agent-centric trajectory modeling.
  arXiv  Detail & Related papers  (2025-06-27T09:50:38Z)
• KG-QAGen: A Knowledge-Graph-Based Framework for Systematic Question Generation and Long-Context LLM Evaluation [3.618621510356872]
  KG-QAGen is a framework that extracts QA pairs at multiple complexity levels.<n>We construct a dataset of 20,139 QA pairs and open-source a part of it.<n>We evaluate 13 proprietary and open-source LLMs and observe that even the best-performing models are struggling with set-based comparisons.
  arXiv  Detail & Related papers  (2025-05-18T16:46:39Z)
• CART: A Generative Cross-Modal Retrieval Framework with Coarse-To-Fine Semantic Modeling [53.97609687516371]
  Cross-modal retrieval aims to search for instances, which are semantically related to the query through the interaction of different modal data.<n>Traditional solutions utilize a single-tower or dual-tower framework to explicitly compute the score between queries and candidates.<n>We propose a generative cross-modal retrieval framework (CART) based on coarse-to-fine semantic modeling.
  arXiv  Detail & Related papers  (2024-06-25T12:47:04Z)
• An Empirical Study of Multimodal Model Merging [148.48412442848795]
  Model merging is a technique that fuses multiple models trained on different tasks to generate a multi-task solution. We conduct our study for a novel goal where we can merge vision, language, and cross-modal transformers of a modality-specific architecture. We propose two metrics that assess the distance between weights to be merged and can serve as an indicator of the merging outcomes.
  arXiv  Detail & Related papers  (2023-04-28T15:43:21Z)
• Few-Shot Named Entity Recognition: A Comprehensive Study [92.40991050806544]
  We investigate three schemes to improve the model generalization ability for few-shot settings. We perform empirical comparisons on 10 public NER datasets with various proportions of labeled data. We create new state-of-the-art results on both few-shot and training-free settings.
  arXiv  Detail & Related papers  (2020-12-29T23:43:16Z)
• Keyphrase Extraction with Dynamic Graph Convolutional Networks and Diversified Inference [50.768682650658384]
  Keyphrase extraction (KE) aims to summarize a set of phrases that accurately express a concept or a topic covered in a given document. Recent Sequence-to-Sequence (Seq2Seq) based generative framework is widely used in KE task, and it has obtained competitive performance on various benchmarks. In this paper, we propose to adopt the Dynamic Graph Convolutional Networks (DGCN) to solve the above two problems simultaneously.
  arXiv  Detail & Related papers  (2020-10-24T08:11:23Z)
• DHOG: Deep Hierarchical Object Grouping [0.0]
  We show that greedy or local methods of maximising mutual information (such as gradient optimisation) discover local optima of the mutual information criterion. We introduce deep hierarchical object grouping (DHOG) that computes a number distinct discrete representations of images in a hierarchical order. We find that these representations align better with the downstream task of grouping into underlying object classes.
  arXiv  Detail & Related papers  (2020-03-13T14:11:48Z)

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.