Saved in:
Bibliographic Details
Main Authors: Wu, Zhanyu, Zhang, Richong, Nie, Zhijie
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2602.03306
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912886913236992
author Wu, Zhanyu
Zhang, Richong
Nie, Zhijie
author_facet Wu, Zhanyu
Zhang, Richong
Nie, Zhijie
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2602_03306
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Learning to Select: Query-Aware Adaptive Dimension Selection for Dense Retrieval
Wu, Zhanyu
Zhang, Richong
Nie, Zhijie
Information Retrieval
Artificial Intelligence
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.
title Learning to Select: Query-Aware Adaptive Dimension Selection for Dense Retrieval
topic Information Retrieval
Artificial Intelligence
url https://arxiv.org/abs/2602.03306