# Flexible retrieval with NMSLIB and FlexNeuART

arXiv: https://arxiv.org/abs/2010.14848 · HTML: https://mlsanity.com/paper/2010.14848/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Oct 2020.

## Built on by (most cited first, 14 of 14)

- [Extreme Multi-label Learning for Semantic Matching in Product Search](https://mlsanity.com/paper/2106.12657/) (2021)
- [A Proposed Conceptual Framework for a Representational Approach to Information Retrieval](https://mlsanity.com/paper/2110.01529/) (2021)
- [In Defense of Cross-Encoders for Zero-Shot Retrieval](https://mlsanity.com/paper/2212.06121/) (2022)
- [InPars-Light: Cost-Effective Unsupervised Training of Efficient Rankers](https://mlsanity.com/paper/2301.02998/) (2023)
- [A Systematic Evaluation of Transfer Learning and Pseudo-labeling with BERT-based Ranking Models](https://mlsanity.com/paper/2103.03335/) (2021)
- [KazQAD: Kazakh Open-Domain Question Answering Dataset](https://mlsanity.com/paper/2404.04487/) (2024)
- [Query Encoder Distillation via Embedding Alignment is a Strong Baseline Method to Boost Dense Retriever Online Efficiency](https://mlsanity.com/paper/2306.11550/) (2023)
- [Composite Code Sparse Autoencoders for first stage retrieval](https://mlsanity.com/paper/2204.07023/) (2022)
- [Exploring Classic and Neural Lexical Translation Models for Information Retrieval: Interpretability, Effectiveness, and Efficiency Benefits](https://mlsanity.com/paper/2102.06815/) (2021)
- [Positional Bias in Long-Document Ranking: Impact, Assessment, and Mitigation](https://mlsanity.com/paper/2207.01262/) (2022)
- [SPRINT: A Unified Toolkit for Evaluating and Demystifying Zero-shot Neural Sparse Retrieval](https://mlsanity.com/paper/2307.10488/) (2023)
- [MrRank: Improving Question Answering Retrieval System through Multi-Result Ranking Model](https://mlsanity.com/paper/2406.05733/) (2024)
- [RoutIR: Fast Serving of Retrieval Pipelines for Retrieval-Augmented Generation](https://mlsanity.com/paper/2601.10644/) (2026)
- [LaSER: Language-Specific Event Recommendation](https://mlsanity.com/paper/2303.04712/) (2023)

## Abstract (arXiv)

Our objective is to introduce to the NLP community an existing k-NN search library NMSLIB, a new retrieval toolkit FlexNeuART, as well as their integration capabilities. NMSLIB, while being one the fastest k-NN search libraries, is quite generic and supports a variety of distance/similarity functions. Because the library relies on the distance-based structure-agnostic algorithms, it can be further extended by adding new distances. FlexNeuART is a modular, extendible and flexible toolkit for candidate generation in IR and QA applications, which supports mixing of classic and neural ranking signals. FlexNeuART can efficiently retrieve mixed dense and sparse representations (with weights learned from training data), which is achieved by extending NMSLIB. In that, other retrieval systems work with purely sparse representations (e.g., Lucene), purely dense representations (e.g., FAISS and Annoy), or only perform mixing at the re-ranking stage.