# Pyserini: An Easy-to-Use Python Toolkit to Support Replicable IR Research with Sparse and Dense Representations

arXiv: https://arxiv.org/abs/2102.10073 · HTML: https://mlsanity.com/paper/2102.10073/

## Key facts

- Cited by 60 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Feb 2021.

## Built on by (most cited first, 30 of 60)

- [WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents](https://mlsanity.com/paper/2207.01206/) (2022)
- [Simple Entity-Centric Questions Challenge Dense Retrievers](https://mlsanity.com/paper/2109.08535/) (2021)
- [Investigating Data Contamination in Modern Benchmarks for Large Language Models](https://mlsanity.com/paper/2311.09783/) (2023)
- [InstructRAG: Instructing Retrieval-Augmented Generation via Self-Synthesized Rationales](https://mlsanity.com/paper/2406.13629/) (2024)
- [InPars-v2: Large Language Models as Efficient Dataset Generators for Information Retrieval](https://mlsanity.com/paper/2301.01820/) (2023)
- [The Web Is Your Oyster - Knowledge-Intensive NLP against a Very Large Web Corpus](https://mlsanity.com/paper/2112.09924/) (2021)
- [One Question Answering Model for Many Languages with Cross-lingual Dense Passage Retrieval](https://mlsanity.com/paper/2107.11976/) (2021)
- [Learning to Retrieve Passages without Supervision](https://mlsanity.com/paper/2112.07708/) (2021)
- [A Replication Study of Dense Passage Retriever](https://mlsanity.com/paper/2104.05740/) (2021)
- [The Chronicles of RAG: The Retriever, the Chunk and the Generator](https://mlsanity.com/paper/2401.07883/) (2024)
- [Unveiling the Spectrum of Data Contamination in Language Models: A Survey from Detection to Remediation](https://mlsanity.com/paper/2406.14644/) (2024)
- [WebBrain: Learning to Generate Factually Correct Articles for Queries by Grounding on Large Web Corpus](https://mlsanity.com/paper/2304.04358/) (2023)
- [Simplified Data Wrangling with ir_datasets](https://mlsanity.com/paper/2103.02280/) (2021)
- [Multi-CPR: A Multi Domain Chinese Dataset for Passage Retrieval](https://mlsanity.com/paper/2203.03367/) (2022)
- [Yes, BM25 is a Strong Baseline for Legal Case Retrieval](https://mlsanity.com/paper/2105.05686/) (2021)
- [RAG-RLRC-LaySum at BioLaySumm: Integrating Retrieval-Augmented Generation and Readability Control for Layman Summarization of Biomedical Texts](https://mlsanity.com/paper/2405.13179/) (2024)
- [In Defense of Cross-Encoders for Zero-Shot Retrieval](https://mlsanity.com/paper/2212.06121/) (2022)
- [Improving Biomedical Information Retrieval with Neural Retrievers](https://mlsanity.com/paper/2201.07745/) (2022)
- [Utilizing BERT for Information Retrieval: Survey, Applications, Resources, and Challenges](https://mlsanity.com/paper/2403.00784/) (2024)
- [Saving Dense Retriever from Shortcut Dependency in Conversational Search](https://mlsanity.com/paper/2202.07280/) (2022)
- [LexRAG: Benchmarking Retrieval-Augmented Generation in Multi-Turn Legal Consultation Conversation](https://mlsanity.com/paper/2502.20640/) (2025)
- [No Parameter Left Behind: How Distillation and Model Size Affect Zero-Shot Retrieval](https://mlsanity.com/paper/2206.02873/) (2022)
- [LLM-RankFusion: Mitigating Intrinsic Inconsistency in LLM-based Ranking](https://mlsanity.com/paper/2406.00231/) (2024)
- [Adaptive Query Rewriting: Aligning Rewriters through Marginal Probability of Conversational Answers](https://mlsanity.com/paper/2406.10991/) (2024)
- [Improving Wikipedia Verifiability with AI](https://mlsanity.com/paper/2207.06220/) (2022)
- [Natural Logic-guided Autoregressive Multi-hop Document Retrieval for Fact Verification](https://mlsanity.com/paper/2212.05276/) (2022)
- [Investigating the Robustness of Retrieval-Augmented Generation at the Query Level](https://mlsanity.com/paper/2507.06956/) (2025)
- [DeAR: Dual-Stage Document Reranking with Reasoning Agents via LLM Distillation](https://mlsanity.com/paper/2508.16998/) (2025)
- [CSPLADE: Learned Sparse Retrieval with Causal Language Models](https://mlsanity.com/paper/2504.10816/) (2025)
- [Encoder Adaptation of Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2110.01599/) (2021)

## Abstract (arXiv)

Pyserini is an easy-to-use Python toolkit that supports replicable IR research by providing effective first-stage retrieval in a multi-stage ranking architecture. Our toolkit is self-contained as a standard Python package and comes with queries, relevance judgments, pre-built indexes, and evaluation scripts for many commonly used IR test collections. We aim to support, out of the box, the entire research lifecycle of efforts aimed at improving ranking with modern neural approaches. In particular, Pyserini supports sparse retrieval (e.g., BM25 scoring using bag-of-words representations), dense retrieval (e.g., nearest-neighbor search on transformer-encoded representations), as well as hybrid retrieval that integrates both approaches. This paper provides an overview of toolkit features and presents empirical results that illustrate its effectiveness on two popular ranking tasks. We also describe how our group has built a culture of replicability through shared norms and tools that enable rigorous automated testing.