Efficiency Optimizations for Superblock-based Sparse Retrieval

2026-02-02

AI Summary

This work addresses the inefficiency of query processing in hypercube-based sparse retrieval by proposing a low-overhead hypercube pruning strategy that integrates a compact index structure with a general zero-shot configuration. Without relying on task-specific fine-tuning, the method substantially reduces scoring overhead while maintaining competitive retrieval effectiveness. Leveraging language model–driven sparse representations, it effectively balances efficiency and relevance. Extensive experiments on MS MARCO and multiple BEIR datasets demonstrate that the proposed approach consistently achieves efficient and stable query acceleration across various sparse retrieval models, preserving strong retrieval performance.

Technology Category

• Data Mining & Knowledge Management: Intelligent Query Processing
• Search and Optimization: Learning to Search
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• Graph Algorithms and Modeling for the Web: Querying, indexing, and retrieval in Web-related graphs
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Learned sparse retrieval (LSR) is a popular method for first-stage retrieval because it combines the semantic matching of language models with efficient CPU-friendly algorithms. Previous work aggregates blocks into"superblocks"to quickly skip the visitation of blocks during query processing by using an advanced pruning heuristic. This paper proposes a simple and effective superblock pruning scheme that reduces the overhead of superblock score computation while preserving competitive relevance. It combines this scheme with a compact index structure and a robust zero-shot configuration that is effective across LSR models and multiple datasets. This paper provides an analytical justification and evaluation on the MS MARCO and BEIR datasets, demonstrating that the proposed scheme can be a strong alternative for efficient sparse retrieval.

Problem

• sparse retrieval
• superblock
• efficiency optimization
• pruning
• first-stage retrieval

Innovation

• superblock pruning
• learned sparse retrieval
• efficient retrieval
• compact index
• zero-shot configuration