# SPLADE-v3: New baselines for SPLADE

arXiv: https://arxiv.org/abs/2403.06789 · HTML: https://mlsanity.com/paper/2403.06789/

## Key facts

- Cited by 72 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 20 references that are in the map.
- First posted on arXiv 11 Mar 2024.

## Builds on (most cited first, 16 of 16)

- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models](https://mlsanity.com/paper/2104.08663/) (2021)
- [ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interaction](https://mlsanity.com/paper/2112.01488/) (2021)
- [SPLADE: Sparse Lexical and Expansion Model for First Stage Ranking](https://mlsanity.com/paper/2107.05720/) (2021)
- [Unsupervised Corpus Aware Language Model Pre-training for Dense Passage Retrieval](https://mlsanity.com/paper/2108.05540/) (2021)
- [Improving Efficient Neural Ranking Models with Cross-Architecture Knowledge Distillation](https://mlsanity.com/paper/2010.02666/) (2020)
- [SPLADE v2: Sparse Lexical and Expansion Model for Information Retrieval](https://mlsanity.com/paper/2109.10086/) (2021)
- [From Distillation to Hard Negative Sampling: Making Sparse Neural IR Models More Effective](https://mlsanity.com/paper/2205.04733/) (2022)
- [Distilling Dense Representations for Ranking using Tightly-Coupled Teachers](https://mlsanity.com/paper/2010.11386/) (2020)
- [Tevatron: An Efficient and Flexible Toolkit for Dense Retrieval](https://mlsanity.com/paper/2203.05765/) (2022)
- [Curriculum Learning for Dense Retrieval Distillation](https://mlsanity.com/paper/2204.13679/) (2022)
- [Simplified Data Wrangling with ir_datasets](https://mlsanity.com/paper/2103.02280/) (2021)
- [An Efficiency Study for SPLADE Models](https://mlsanity.com/paper/2207.03834/) (2022)
- [Benchmarking Middle-Trained Language Models for Neural Search](https://mlsanity.com/paper/2306.02867/) (2023)
- [The tale of two MS MARCO -- and their unfair comparisons](https://mlsanity.com/paper/2304.12904/) (2023)
- [Ranger: A Toolkit for Effect-Size Based Multi-Task Evaluation](https://mlsanity.com/paper/2305.15048/) (2023)

## Built on by (most cited first, 30 of 72)

- [A Survey on Retrieval-Augmented Text Generation for Large Language Models](https://mlsanity.com/paper/2404.10981/) (2024)
- [Ragnar"ok: A Reusable RAG Framework and Baselines for TREC 2024 Retrieval-Augmented Generation Track](https://mlsanity.com/paper/2406.16828/) (2024)
- [Rank-K: Test-Time Reasoning for Listwise Reranking](https://mlsanity.com/paper/2505.14432/) (2025)
- [Context Embeddings for Efficient Answer Generation in RAG](https://mlsanity.com/paper/2407.09252/) (2024)
- [PeerQA: A Scientific Question Answering Dataset from Peer Reviews](https://mlsanity.com/paper/2502.13668/) (2025)
- [RetroLLM: Empowering Large Language Models to Retrieve Fine-grained Evidence within Generation](https://mlsanity.com/paper/2412.11919/) (2024)
- [PISCO: Pretty Simple Compression for Retrieval-Augmented Generation](https://mlsanity.com/paper/2501.16075/) (2025)
- [JaColBERTv2.5: Optimising Multi-Vector Retrievers to Create State-of-the-Art Japanese Retrievers with Constrained Resources](https://mlsanity.com/paper/2407.20750/) (2024)
- [CSPLADE: Learned Sparse Retrieval with Causal Language Models](https://mlsanity.com/paper/2504.10816/) (2025)
- [DiSCo: LLM Knowledge Distillation for Efficient Sparse Retrieval in Conversational Search](https://mlsanity.com/paper/2410.14609/) (2024)
- [Mistral-SPLADE: LLMs for better Learned Sparse Retrieval](https://mlsanity.com/paper/2408.11119/) (2024)
- [rerankers: A Lightweight Python Library to Unify Ranking Methods](https://mlsanity.com/paper/2408.17344/) (2024)
- [Towards Competitive Search Relevance For Inference-Free Learned Sparse Retrievers](https://mlsanity.com/paper/2411.04403/) (2024)
- [Decoding Dense Embeddings: Sparse Autoencoders for Interpreting and Discretizing Dense Retrieval](https://mlsanity.com/paper/2506.00041/) (2025)
- [Revisiting Text Ranking in Deep Research](https://mlsanity.com/paper/2602.21456/) (2026)
- [Enhancing Lexicon-Based Text Embeddings with Large Language Models](https://mlsanity.com/paper/2501.09749/) (2025)
- [Learning Retrieval Models with Sparse Autoencoders](https://mlsanity.com/paper/2603.13277/) (2026)
- [LACONIC: Dense-Level Effectiveness for Scalable Sparse Retrieval via a Two-Phase Training Curriculum](https://mlsanity.com/paper/2601.01684/) (2026)
- [OSCAR: Online Soft Compression And Reranking](https://mlsanity.com/paper/2504.07109/) (2025)
- [Balancing the Blend: An Experimental Analysis of Trade-offs in Hybrid Search](https://mlsanity.com/paper/2508.01405/) (2025)
- [LEAF: Knowledge Distillation of Text Embedding Models with Teacher-Aligned Representations](https://mlsanity.com/paper/2509.12539/) (2025)
- [Dense Retrieval for Low Resource Languages -- the Case of Amharic Language](https://mlsanity.com/paper/2503.18570/) (2025)
- [An Alternative to FLOPS Regularization to Effectively Productionize SPLADE-Doc](https://mlsanity.com/paper/2505.15070/) (2025)
- [Overview of the TREC 2025 Retrieval Augmented Generation (RAG) Track](https://mlsanity.com/paper/2603.09891/) (2026)
- [Towards Lossless Token Pruning in Late-Interaction Retrieval Models](https://mlsanity.com/paper/2504.12778/) (2025)
- [CLIRudit: Cross-Lingual Information Retrieval of Scientific Documents](https://mlsanity.com/paper/2504.16264/) (2025)
- [Med-R3: Enhancing Medical Retrieval-Augmented Reasoning of LLMs via Progressive Reinforcement Learning](https://mlsanity.com/paper/2507.23541/) (2025)
- [Simple Projection Variants Improve ColBERT Performance](https://mlsanity.com/paper/2510.12327/) (2025)
- [LANCER: LLM Reranking for Nugget Coverage](https://mlsanity.com/paper/2601.22008/) (2026)
- [Scaling Laws for Embedding Dimension in Information Retrieval](https://mlsanity.com/paper/2602.05062/) (2026)

## Abstract (arXiv)

A companion to the release of the latest version of the SPLADE library. We describe changes to the training structure and present our latest series of models -- SPLADE-v3. We compare this new version to BM25, SPLADE++, as well as re-rankers, and showcase its effectiveness via a meta-analysis over more than 40 query sets. SPLADE-v3 further pushes the limit of SPLADE models: it is statistically significantly more effective than both BM25 and SPLADE++, while comparing well to cross-encoder re-rankers. Specifically, it gets more than 40 MRR@10 on the MS MARCO dev set, and improves by 2% the out-of-domain results on the BEIR benchmark.