# BM25S: Orders of magnitude faster lexical search via eager sparse scoring

arXiv: https://arxiv.org/abs/2407.03618 · HTML: https://mlsanity.com/paper/2407.03618/

## Key facts

- Cited by 88 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 27 references that are in the map.
- First posted on arXiv 4 Jul 2024.

## Builds on (most cited first, 8 of 8)

- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing](https://mlsanity.com/paper/1808.06226/) (2018)
- [MS MARCO: A Human Generated MAchine Reading COmprehension Dataset](https://mlsanity.com/paper/1611.09268/) (2016)
- [FEVER: a large-scale dataset for Fact Extraction and VERification](https://mlsanity.com/paper/1803.05355/) (2018)
- [BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models](https://mlsanity.com/paper/2104.08663/) (2021)
- [Fact or Fiction: Verifying Scientific Claims](https://mlsanity.com/paper/2004.14974/) (2020)
- [SPECTER: Document-level Representation Learning using Citation-informed Transformers](https://mlsanity.com/paper/2004.07180/) (2020)
- [CLIMATE-FEVER: A Dataset for Verification of Real-World Climate Claims](https://mlsanity.com/paper/2012.00614/) (2020)

## Built on by (most cited first, 30 of 88)

- [From RAG to Memory: Non-Parametric Continual Learning for Large Language Models](https://mlsanity.com/paper/2502.14802/) (2025)
- [On the Theoretical Limitations of Embedding-Based Retrieval](https://mlsanity.com/paper/2508.21038/) (2025)
- [Rank1: Test-Time Compute for Reranking in Information Retrieval](https://mlsanity.com/paper/2502.18418/) (2025)
- [Retrieval Models Aren't Tool-Savvy: Benchmarking Tool Retrieval for Large Language Models](https://mlsanity.com/paper/2503.01763/) (2025)
- [Promptriever: Instruction-Trained Retrievers Can Be Prompted Like Language Models](https://mlsanity.com/paper/2409.11136/) (2024)
- [Does Representation Matter? Exploring Intermediate Layers in Large Language Models](https://mlsanity.com/paper/2412.09563/) (2024)
- [ViDoRe V3: A Comprehensive Evaluation of Retrieval Augmented Generation in Complex Real-World Scenarios](https://mlsanity.com/paper/2601.08620/) (2026)
- [Jina-ColBERT-v2: A General-Purpose Multilingual Late Interaction Retriever](https://mlsanity.com/paper/2408.16672/) (2024)
- [R3-RAG: Learning Step-by-Step Reasoning and Retrieval for LLMs via Reinforcement Learning](https://mlsanity.com/paper/2505.23794/) (2025)
- [FunnelRAG: A Coarse-to-Fine Progressive Retrieval Paradigm for RAG](https://mlsanity.com/paper/2410.10293/) (2024)
- [Explicit v.s. Implicit Memory: Exploring Multi-hop Complex Reasoning Over Personalized Information](https://mlsanity.com/paper/2508.13250/) (2025)
- [FocusAgent: Simple Yet Effective Ways of Trimming the Large Context of Web Agents](https://mlsanity.com/paper/2510.03204/) (2025)
- [The RAG Paradox: A Black-Box Attack Exploiting Unintentional Vulnerabilities in Retrieval-Augmented Generation Systems](https://mlsanity.com/paper/2502.20995/) (2025)
- [Compositional Translation: A Novel LLM-based Approach for Low-resource Machine Translation](https://mlsanity.com/paper/2503.04554/) (2025)
- [A General Framework for Producing Interpretable Semantic Text Embeddings](https://mlsanity.com/paper/2410.03435/) (2024)
- [GRADA: Graph-based Reranking against Adversarial Documents Attack](https://mlsanity.com/paper/2505.07546/) (2025)
- [STRUCTSENSE: A Task-Agnostic Agentic Framework for Structured Information Extraction with Human-In-The-Loop Evaluation and Benchmarking](https://mlsanity.com/paper/2507.03674/) (2025)
- [MEMERAG: A Multilingual End-to-End Meta-Evaluation Benchmark for Retrieval Augmented Generation](https://mlsanity.com/paper/2502.17163/) (2025)
- [KoBLEX: Open Legal Question Answering with Multi-hop Reasoning](https://mlsanity.com/paper/2509.01324/) (2025)
- [InfoAgent: Advancing Autonomous Information-Seeking Agents](https://mlsanity.com/paper/2509.25189/) (2025)
- [LAD-RAG: Layout-aware Dynamic RAG for Visually-Rich Document Understanding](https://mlsanity.com/paper/2510.07233/) (2025)
- [ToolDreamer: Instilling LLM Reasoning Into Tool Retrievers](https://mlsanity.com/paper/2510.19791/) (2025)
- [Towards Retrieving Interaction Spaces for Agentic Search](https://mlsanity.com/paper/2606.06880/) (2026)
- [GuRE:Generative Query REwriter for Legal Passage Retrieval](https://mlsanity.com/paper/2505.12950/) (2025)
- [Task-Specific Data Selection for Instruction Tuning via Monosemantic Neuronal Activations](https://mlsanity.com/paper/2503.15573/) (2025)
- [RAG or Fine-tuning? A Comparative Study on LCMs-based Code Completion in Industry](https://mlsanity.com/paper/2505.15179/) (2025)
- [A Deep Dive into Retrieval-Augmented Generation for Code Completion: Experience on WeChat](https://mlsanity.com/paper/2507.18515/) (2025)
- [FinGEAR: Financial Mapping-Guided Enhanced Answer Retrieval](https://mlsanity.com/paper/2509.12042/) (2025)
- [JEF-Hinter: Leveraging Offline Knowledge for Improving Web Agents Adaptation](https://mlsanity.com/paper/2510.04373/) (2025)
- [Multi-Field Adaptive Retrieval](https://mlsanity.com/paper/2410.20056/) (2024)

## Abstract (arXiv)

We introduce BM25S, an efficient Python-based implementation of BM25 that only depends on Numpy and Scipy. BM25S achieves up to a 500x speedup compared to the most popular Python-based framework by eagerly computing BM25 scores during indexing and storing them into sparse matrices. It also achieves considerable speedups compared to highly optimized Java-based implementations, which are used by popular commercial products. Finally, BM25S reproduces the exact implementation of five BM25 variants based on Kamphuis et al. (2020) by extending eager scoring to non-sparse variants using a novel score shifting method. The code can be found at https://github.com/xhluca/bm25s