Learning to Select: Query-Aware Adaptive Dimension Selection for Dense Retrieval

• URL: http://arxiv.org/abs/2602.03306v2
• Date: Sat, 07 Feb 2026 10:25:02 GMT
• Title: Learning to Select: Query-Aware Adaptive Dimension Selection for Dense Retrieval
• Authors: Zhanyu Wu, Richong Zhang, Zhijie Nie,
• Abstract summary: We propose a Query-Aware Adaptive Dimension Selection framework.<n>We first construct dimension importance over embedding dimensions using supervised relevance labels, and then train a predictor to map a query embedding to these label-distilled importance scores.<n>At inference, the predictor selects a query-aware subset of dimensions for similarity based solely on the query embedding, without pseudo-relevance feedback.
• Score: 37.24586920652237
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Dense retrieval represents queries and documents as high-dimensional embeddings, but these representations can be redundant at the query level: for a given information need, only a subset of dimensions is consistently helpful for ranking. Prior work addresses this via pseudo-relevance feedback (PRF) based dimension importance estimation, which can produce query-aware masks without labeled data but often relies on noisy pseudo signals and heuristic test-time procedures. In contrast, supervised adapter methods leverage relevance labels to improve embedding quality, yet they learn global transformations shared across queries and do not explicitly model query-aware dimension importance. We propose a Query-Aware Adaptive Dimension Selection framework that \emph{learns} to predict per-dimension importance directly from query embedding. We first construct oracle dimension importance distributions over embedding dimensions using supervised relevance labels, and then train a predictor to map a query embedding to these label-distilled importance scores. At inference, the predictor selects a query-aware subset of dimensions for similarity computation based solely on the query embedding, without pseudo-relevance feedback. Experiments across multiple dense retrievers and benchmarks show that our learned dimension selector improves retrieval effectiveness over the full-dimensional baseline as well as PRF-based masking and supervised adapter baselines.

Related papers

• Reveal Hidden Pitfalls and Navigate Next Generation of Vector Similarity Search from Task-Centric Views [24.456069497637035]
  Vector Similarity Search (VSS) in high-dimensional spaces is rapidly emerging as core functionality in next-generation database systems.<n>Current benchmarks evaluate VSS primarily on the recall-latency trade-off against a ground truth defined solely by distance metrics.<n>We present Iceberg, a holistic benchmark suite for end-to-end evaluation of VSS methods in realistic application contexts.
  arXiv  Detail & Related papers  (2025-12-15T04:49:33Z)
• Evaluating Embedding Models and Pipeline Optimization for AI Search Quality [0.0]
  We evaluate the performance of various text embedding models and pipeline configurations for AI-driven search systems.<n>A custom evaluation dataset of 11,975 query-chunk pairs was synthesized from US City Council meeting transcripts.
  arXiv  Detail & Related papers  (2025-11-27T09:09:39Z)
• Query Decomposition for RAG: Balancing Exploration-Exploitation [83.79639293409802]
  RAG systems address complex user requests by decomposing them into subqueries, retrieving potentially relevant documents for each, and then aggregating them to generate an answer.<n>We formulate query decomposition and document retrieval in an exploitation-exploration setting, where retrieving one document at a time builds a belief about the utility of a given sub-queries.<n>Our main finding is that estimating document relevance using rank information and human judgments yields a 35% gain in document-level precision, 15% increase in alpha-nDCG, and better performance on the downstream task of long-form generation.
  arXiv  Detail & Related papers  (2025-10-21T13:37:11Z)
• ACE: A Cardinality Estimator for Set-Valued Queries [35.31790118566289]
  We propose an Attention-based Cardinality Estorimator for estimating the cardinality of queries over set-valued data.<n>To handle variable-sized queries, a pooling module is introduced, followed by a regression model (MLP) to generate final cardinality estimates.
  arXiv  Detail & Related papers  (2025-03-19T06:29:15Z)
• ReTreever: Tree-based Coarse-to-Fine Representations for Retrieval [64.44265315244579]
  We propose a tree-based method for organizing and representing reference documents at various granular levels.<n>Our method, called ReTreever, jointly learns a routing function per internal node of a binary tree such that query and reference documents are assigned to similar tree branches.<n>Our evaluations show that ReTreever generally preserves full representation accuracy.
  arXiv  Detail & Related papers  (2025-02-11T21:35:13Z)
• ECLIPSE: Contrastive Dimension Importance Estimation with Pseudo-Irrelevance Feedback for Dense Retrieval [14.72046677914345]
  Recent advances in Information Retrieval have leveraged high-dimensional embedding spaces to improve the retrieval of relevant documents.<n>Despite these high-dimensional representations, documents relevant to a query reside on a lower-dimensional, query-dependent manifold.<n>We propose a novel methodology that addresses these limitations by leveraging information from both relevant and non-relevant documents.
  arXiv  Detail & Related papers  (2024-12-19T15:45:06Z)
• BRIGHT: A Realistic and Challenging Benchmark for Reasoning-Intensive Retrieval [54.54576644403115]
  We introduce BRIGHT, the first text retrieval benchmark that requires intensive reasoning to retrieve relevant documents.<n>Our dataset consists of 1,384 real-world queries spanning diverse domains, such as economics, psychology, mathematics, and coding.<n>We show that incorporating explicit reasoning about the query improves retrieval performance by up to 12.2 points.
  arXiv  Detail & Related papers  (2024-07-16T17:58:27Z)
• Optimization of Retrieval-Augmented Generation Context with Outlier Detection [0.0]
  We focus on methods to reduce the size and improve the quality of the prompt context required for question-answering systems. Our goal is to select the most semantically relevant documents, treating the discarded ones as outliers. It was found that the greatest improvements were achieved with increasing complexity of the questions and answers.
  arXiv  Detail & Related papers  (2024-07-01T15:53:29Z)
• Database-Augmented Query Representation for Information Retrieval [71.41745087624528]
  We present a novel retrieval framework called Database-Augmented Query representation (DAQu)<n>DAQu augments the original query with various (query-related) metadata across multiple tables.<n>We validate our DAQu in diverse retrieval scenarios, demonstrating that it significantly enhances overall retrieval performance.
  arXiv  Detail & Related papers  (2024-06-23T05:02:21Z)
• A Deep Dive into the Trade-Offs of Parameter-Efficient Preference Alignment Techniques [63.10251271444959]
  Large language models are first pre-trained on trillions of tokens and then instruction-tuned or aligned to specific preferences. We conduct an in-depth investigation of the impact of popular choices for three crucial axes. Our setup spanning over 300 experiments reveals consistent trends and unexpected findings.
  arXiv  Detail & Related papers  (2024-06-07T12:25:51Z)
• User Intent Recognition and Semantic Cache Optimization-Based Query Processing Framework using CFLIS and MGR-LAU [0.0]
  This work analyzed the informational, navigational, and transactional-based intents in queries for enhanced QP. For efficient QP, the data is structured using Epanechnikov Kernel-Ordering Points To Identify the Clustering Structure (EK-OPTICS) The extracted features, detected intents and structured data are inputted to the Multi-head Gated Recurrent Learnable Attention Unit (MGR-LAU)
  arXiv  Detail & Related papers  (2024-06-06T20:28:05Z)
• Generative Retrieval as Multi-Vector Dense Retrieval [71.75503049199897]
  Generative retrieval generates identifiers of relevant documents in an end-to-end manner. Prior work has demonstrated that generative retrieval with atomic identifiers is equivalent to single-vector dense retrieval. We show that generative retrieval and multi-vector dense retrieval share the same framework for measuring the relevance to a query of a document.
  arXiv  Detail & Related papers  (2024-03-31T13:29:43Z)
• Selecting Query-bag as Pseudo Relevance Feedback for Information-seeking Conversations [76.70349332096693]
  Information-seeking dialogue systems are widely used in e-commerce systems. We propose a Query-bag based Pseudo Relevance Feedback framework (QB-PRF) It constructs a query-bag with related queries to serve as pseudo signals to guide information-seeking conversations.
  arXiv  Detail & Related papers  (2024-03-22T08:10:32Z)
• Improving Query Representations for Dense Retrieval with Pseudo Relevance Feedback [29.719150565643965]
  This paper proposes ANCE-PRF, a new query encoder that uses pseudo relevance feedback (PRF) to improve query representations for dense retrieval. ANCE-PRF uses a BERT encoder that consumes the query and the top retrieved documents from a dense retrieval model, ANCE, and it learns to produce better query embeddings directly from relevance labels. Analysis shows that the PRF encoder effectively captures the relevant and complementary information from PRF documents, while ignoring the noise with its learned attention mechanism.
  arXiv  Detail & Related papers  (2021-08-30T18:10:26Z)
• APRF-Net: Attentive Pseudo-Relevance Feedback Network for Query Categorization [12.634704014206294]
  We propose a novel deep neural model named textbfAttentive textbfPseudo textbfRelevance textbfFeedback textbfNetwork (APRF-Net) to enhance the representation of rare queries for query categorization. Our results show that the APRF-Net significantly improves query categorization by 5.9% on $F1@1$ score over the baselines, which increases to 8.2% improvement for the rare queries.
  arXiv  Detail & Related papers  (2021-04-23T02:34:08Z)
• Improving significance of binary black hole mergers in Advanced LIGO data using deep learning : Confirmation of GW151216 [0.0]
  We present a novel Machine Learning (ML) based strategy to search for binary black hole (BBH) mergers in data from ground-based gravitational wave (GW) observatories. This is the first ML-based search that not only recovers all the compact binary coalescences (CBCs) in the first GW transients catalog (GWTC-1), but also makes a clean detection of GW151216.
  arXiv  Detail & Related papers  (2020-10-16T18:27:48Z)

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.