Efficient Sparse Retrieval with Lightweight Superblock Pruning
Parker Carlson, Wentai Xie, Rohil Shah, Tao Yang
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.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
1 top-tier paper has cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- Adaptive Sparsity Optimization with Learnable Soft Top-K and Per-Term Thresholding for Efficient Retrieval cites Efficient Inverted Indexes for Approximate Retrieval over Learned Sparse Representations
- Adaptive Sparsity Optimization with Learnable Soft Top-K and Per-Term Thresholding for Efficient Retrieval cites Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
- SimLM: Pre-training with Representation Bottleneck for Dense Passage Retrieval cites Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
Cited by top-tier papers1
Builds on7
- Retrieval-Augmented Generation for Knowledge-Intensive NLP TasksPatrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni et al.NeurIPS 2020 · 19,162 citations
- Efficient Inverted Indexes for Approximate Retrieval over Learned Sparse RepresentationsSebastian Bruch, Franco Maria Nardini, Cosimo Rulli, Rossano VenturiniSIGIR 2024 · 47 citations
- SimLM: Pre-training with Representation Bottleneck for Dense Passage RetrievalLiang Wang, Nan Yang, Xiaolong Huang, Binxing Jiao et al.ACL 2023 · 41 citations
- Accelerating Learned Sparse Indexes Via Term Impact DecompositionJoel Mackenzie, Antonio Mallia, Alistair Moffat, Matthias PetriEMNLP Findings 2022 · 23 citations
- Optimizing Guided Traversal for Fast Learned Sparse RetrievalYifan Qiao, Yingrui Yang, Haixin Lin, Tao YangWWW 2023 · 19 citations
Related papers
- Making Large Language Models Efficient Dense RetrieversYibin Lei, Shwai He, Ang Li, Andrew YatesACL 2026 · 2 citations
- No More K-means: Single-Stage Sparse Coding for Efficient Multi-Vector RetrievalLixuan Guo, Yifei Wang, Tiansheng Wen, Aosong Feng et al.ICML 2026
- Self-Improving Sparse Retrieval Through Heuristic Representation Refinement and Representation-Focused LearningXiaojing Li, Bin Wang, Xiaochun Yang, Meng LuoAAAI 2026
- PromptReps: Prompting Large Language Models to Generate Dense and Sparse Representations for Zero-Shot Document RetrievalShengyao Zhuang, Xueguang Ma, Bevan Koopman, Jimmy Lin et al.EMNLP 2024 · 26 citations
- A Thorough Examination on Zero-shot Dense RetrievalRuiyang Ren, Yingqi Qu, Jing Liu, Xin Zhao et al.EMNLP Findings 2023 · 27 citations
