A Voronoi Cell Formulation for Principled Token Pruning in Late-Interaction Retrieval Models

• URL: http://arxiv.org/abs/2603.09933v2
• Date: Wed, 11 Mar 2026 10:15:41 GMT
• Title: A Voronoi Cell Formulation for Principled Token Pruning in Late-Interaction Retrieval Models
• Abstract summary: Late-interaction models like ColBERT require storing a dense embedding for each document token.<n>Past works address this by attempting to prune low-importance token embeddings based on statistical and empirical measures.<n>We introduce a framework grounded in hyperspace geometry and cast token pruning as a Voronoi cell estimation problem in the embedding space.
• Score: 15.555245312638151
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Late-interaction models like ColBERT offer a competitive performance across various retrieval tasks, but require storing a dense embedding for each document token, leading to a substantial index storage overhead. Past works address this by attempting to prune low-importance token embeddings based on statistical and empirical measures, but they often either lack formal grounding or are ineffective. To address these shortcomings, we introduce a framework grounded in hyperspace geometry and cast token pruning as a Voronoi cell estimation problem in the embedding space. By interpreting each token's influence as a measure of its Voronoi region, our approach enables principled pruning that retains retrieval quality while reducing index size. Through our experiments, we demonstrate that this approach serves not only as a competitive pruning strategy but also as a valuable tool for improving and interpreting token-level behavior within dense retrieval systems.

Related papers

• Guidance for Prior Change via Density Ratio Estimation [5.018167017476858]
  PriorGuide was introduced as an inference-time guidance method.<n>We propose an unbiased test-time guidance framework that leverages Density Ratio Estimation (DRE) to learn a score guidance term.<n>Our method matches or outperforms PriorGuide on C2ST and MMD in most tasks.
  arXiv  Detail & Related papers  (2026-08-22T02:17:41Z)
• The Crowded Embedding Space: A Mean-Field Mechanism for Emergent Marginalization in Retrieval-Augmented Agents [51.56484100374058]
  We show that the high document density required to serve majority interests can geometrically overcrowd the retrieval neighborhood of a semantically similar minority.<n>We introduce a formal framework to analyze how such goal collisions in dense retrieval induce fundamental performance limits.<n>We prove that such objectives drive the system to self-organize into a state that exclusively serves majority interests.
  arXiv  Detail & Related papers  (2026-06-01T20:40:30Z)
• Greedy Is Enough: Sparse Action Discovery in Agentic LLMs [11.62669179647184]
  empirical evidence suggests that only a small subset of actions meaningfully influences performance in a given deployment.<n>Motivated by this observation, we study a contextual linear reward model in which action is governed by a structured sparsity assumption.<n>Our results identify sparse action discovery as a fundamental principle underlying large-action decision-making.
  arXiv  Detail & Related papers  (2026-01-13T07:15:32Z)
• Bayesian Pliable Lasso with Horseshoe Prior for Interaction Effects in GLMs with Missing Responses [0.0]
  We propose a pliable lasso that places sparsity-inducing priors, such as the horseshoe, on both main and interaction effects.<n>Our framework yields sparse, interpretable interaction structures, and principled measures of uncertainty.<n>Our method is implemented in the package texttthspliable available on Github.
  arXiv  Detail & Related papers  (2025-09-09T08:28:21Z)
• Multiply Robust Conformal Risk Control with Coarsened Data [0.0]
  Conformal Prediction (CP) has recently received a tremendous amount of interest.<n>In this paper, we consider the general problem of obtaining distribution-free valid prediction regions for an outcome given coarsened data.<n>Our principled use of semiparametric theory has the key advantage of facilitating flexible machine learning methods.
  arXiv  Detail & Related papers  (2025-08-21T12:14:44Z)
• Beyond Progress Measures: Theoretical Insights into the Mechanism of Grokking [50.465604300990904]
  Grokking refers to the abrupt improvement in test accuracy after extended overfitting.<n>In this work, we investigate the grokking mechanism underlying the Transformer in the task of prime number operations.
  arXiv  Detail & Related papers  (2025-04-04T04:42:38Z)
• Anti-Collapse Loss for Deep Metric Learning Based on Coding Rate Metric [99.19559537966538]
  DML aims to learn a discriminative high-dimensional embedding space for downstream tasks like classification, clustering, and retrieval. To maintain the structure of embedding space and avoid feature collapse, we propose a novel loss function called Anti-Collapse Loss. Comprehensive experiments on benchmark datasets demonstrate that our proposed method outperforms existing state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-07-03T13:44:20Z)
• Predictive Inference in Multi-environment Scenarios [18.324321417099394]
  We address the challenge of constructing valid confidence intervals and sets in problems of prediction across multiple environments. We extend the jackknife and split-conformal methods to show how to obtain distribution-free coverage in non-traditional, potentially hierarchical data-generating scenarios. Our contributions also include extensions for settings with non-real-valued responses, a theory of consistency for predictive inference in these general problems, and insights on the limits of conditional coverage.
  arXiv  Detail & Related papers  (2024-03-25T00:21:34Z)
• A Fixed-Point Approach to Unified Prompt-Based Counting [51.20608895374113]
  This paper aims to establish a comprehensive prompt-based counting framework capable of generating density maps for objects indicated by various prompt types, such as box, point, and text. Our model excels in prominent class-agnostic datasets and exhibits superior performance in cross-dataset adaptation tasks.
  arXiv  Detail & Related papers  (2024-03-15T12:05:44Z)
• Towards Continual Learning Desiderata via HSIC-Bottleneck Orthogonalization and Equiangular Embedding [55.107555305760954]
  We propose a conceptually simple yet effective method that attributes forgetting to layer-wise parameter overwriting and the resulting decision boundary distortion. Our method achieves competitive accuracy performance, even with absolute superiority of zero exemplar buffer and 1.02x the base model.
  arXiv  Detail & Related papers  (2024-01-17T09:01:29Z)
• Adaptive Cross Batch Normalization for Metric Learning [75.91093210956116]
  Metric learning is a fundamental problem in computer vision. We show that it is equally important to ensure that the accumulated embeddings are up to date. In particular, it is necessary to circumvent the representational drift between the accumulated embeddings and the feature embeddings at the current training iteration.
  arXiv  Detail & Related papers  (2023-03-30T03:22:52Z)
• ROME: Robustifying Memory-Efficient NAS via Topology Disentanglement and Gradient Accumulation [106.04777600352743]
  Differentiable architecture search (DARTS) is largely hindered by its substantial memory cost since the entire supernet resides in the memory. The single-path DARTS comes in, which only chooses a single-path submodel at each step. While being memory-friendly, it also comes with low computational costs. We propose a new algorithm called RObustifying Memory-Efficient NAS (ROME) to give a cure.
  arXiv  Detail & Related papers  (2020-11-23T06:34:07Z)

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.